Knowledge Graph Insights

Veronika Heimsbakk

With interest in knowledge graphs growing by the day, Veronika Heimsbakk is busier than ever with her efforts to connect the data engineering, information architecture, and ontology practices that drive modern knowledge engineering.

Best known as an advanced knowledge graph practitioner and a leading expert on the SHACL standard, Veronika also regularly shares her knowledge through her writing, university courses, and professional workshops.

We talked about:

her work at Data Treehouse, creating tooling for data people to get on board the knowledge graph journey
how she helps data engineers find their overlap with knowledge engineering
her work to build bridges between data engineers, information architects, and ontologists
how she meets data engineers on their own turf by using simple Python scripts to put their data frames into a knowledge graph
how public sector compliance requirements drive demand for RDF solutions
the powerful tool that helps her communicate with a variety of stakeholders and collaborators: coloring pencils
how she works with information architects and enterprise architects
her take on graph visualizations, that they're rarely very useful in helping her communicate with engineers and business people
her approach to balance top-down ontological approaches and bottom up data engineering approaches in knowledge graph construction
her early work with SHACL and her appreciation for its applicability to a wide range of use cases beyond simple data validation
her take on the ongoing OWL versus SHACL discussion
her preferred tool for turning modeling sketches into RDF code: WebProtégé
how her work with the Norwegian maritime authorities reduced caseworker time on regulatory tasks from several weeks to a few seconds
her upcoming masterclass at the Knowledge Graph Conference on transitioning from data engineering to knowledge engineering

Veronika's bio
Veronika Heimsbakk is a knowledge graph specialist at Data Treehouse with over a decade of experience in semantic knowledge graph technologies. Throughout her career as a consultant, she has served as a developer, architect, advisor, and team lead, working with public and private sector clients across Europe, with a strong focus on the public sector in recent years.

Veronika is the author of SHACL for the Practitioner (2025). She is a regular guest lecturer on SHACL at the University of Oslo and has delivered the SHACL Masterclass at various venues for several years. In 2024, she was recognised as one of Norway's Top 50 Women in Tech.

On Substack, Veronika writes From Data Engineering to Knowledge Engineering, a practical article series that shows data engineers how to build knowledge graphs using familiar tools like Python, Polars, and maplib, covering everything from ontologies and SPARQL to SHACL validation and reasoning. An eager advocate for logic and linked data, she champions knowledge graphs in a landscape increasingly dominated by predictive approaches.
Connect with Veronika online

LinkedIn
Substack
SHACL for the Practitioner book
e-mail: sh at veronahe dot no

Video
Here’s the video version of our conversation:

https://youtu.be/cY8rhPoXepE


Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 48. Ontology design and knowledge graph building are truly team sports, requiring collaboration across a variety of business and engineering disciplines. Few practitioners are as experienced at bringing these teams together as Veronika Heimsbakk. As both a consultant and as an author and educator, she helps business and public sector stakeholders, data engineers, and knowledge architects understand each other's languages and appreciate each other's practices.
Interview transcript
Larry:
Hi everyone. Welcome to episode number 48 of the Knowledge Graph Insights podcast. I am extremely delighted today to welcome to the show Veronika Heimsbakk. If you've ever been to the Knowledge Graph Conference, Veronika's just, you know her already. She's just the most engaging presence there. She's always got her Norwegian KitKat bars and her Polaroid camera and doing awesome workshops on SHACL and other things. But welcome to the show, Veronika. Tell folks a little bit more about what you're up to these days.

Veronika:
Thank you, Larry, and thank you for having me. Yes, these days I'm up to in using familiar tooling to get started with knowledge graphs and harvesting all the knowledge graph capabilities and graph traversals as opposed to JOINs and tabular things. Yeah.

Larry:
Well, this feels like a year in which a lot of that might be happening. A lot of data engineers, there just seems to be so much excitement and interest in knowledge graphs and ontologies. And it's so important to meet people where they are on their journey into that. And you know, you're involved with, I know the data folks in Helsinki and we didn't talk about your background. You're currently a knowledge graph specialist at the Data Treehouse. And previously, you've done consulting like at Capgemini. So you've done a lot of this work hands-on. You wrote a book about SHACL, and you do workshops and a lot of teaching. And part of that whole mindset of yours is currently, maybe not... I guess it's focused on helping data engineers become knowledge engineers. Is that an accurate way of putting it?

Veronika:
Or at least not fully transitioning maybe from data engineering to knowledge engineering, but finding that intersection of a skillset that's truly powerful in working with ontologies because we have seen the rapid interest and popularity of ontologies lately when large language models took the world by storm. But I've also experienced during my years as a consultant that the ontology things and the knowledge graph aspects, they are usually a concern of the information architects and those who work with concepts and terms and setting them into context and everything. But the information architecture departments usually don't talk to the people working on the data and making applications. So why should we create ontologies that are machine-readable in semantic models? They are a database schema in itself. They are fully usable by data people, but there is something in between there that's hard to grasp.

Veronika:
So I want to build this bridge because when I was finished at the uni, I started as a Java developer on Symantec Tech project. So I've been doing a little bit of data engineering myself in the early days going from tabular data to RDF and knowledge graphs. But I see that this isn't something that should be separated, of course, if you want to be data-driven, ontology-driven in your applications, you need the data people on board if you're going... Successful project.

Larry:
Yeah, that's really interesting too, because it seems like there's at least a couple of things there. Just the common language between information architects, data engineers, and knowledge engineers, but then also, in any communication project, meeting them on their own ground. And that probably applies both in the human natural language that you're talking to people about, but also in the technology to implement stuff. And I know that's what you're doing in your day job now, but can you talk a little bit about how you're making knowledge graphs and knowledge engineering more accessible to data engineers?

Veronika:
Yes, of course. The company that I work for, we create a framework for doing exactly that, like working with knowledge graphs using data frames. So I've been working a lot with that lately and writing a lot of articles on the topic and how you can transition from a tabular data format to queryable knowledge graph, doing graph traversals and answering questions you even didn't know you had, right? But the way that I work is usually together with clients, is applying simple tooling on their tabular data. And these days, most people work in data frames, right. So going from a Polars data frame to queryable knowledge graphs only require three, four lines of Python code by using, for example, maplib, which is a Python framework for handling knowledge graphs as data frames. And you can even get your SPARQL query answers back as a data frame to push further in your data pipeline.

Veronika:
So you have all these capabilities of graph traversal in answering questions, but also, in inference and enrichment and automating enrichment of completing metadata, for example, and doing validation with SHACL, for example. You have all these knowledge graph capabilities that you can put on top of your existing data infrastructure.

Larry:
Are there classic use cases where... Is there higher demand in some industry verticals for this kind of thing?

Veronika:
Recently, in Norway at least, I've seen a rapid demand for like, "Hey, I have all my data in this data lake," like Databricks or Snowflake or whatever. But the information architecture folks, they're building ontologies or they want to reuse the national standards. Like in Norway, we have a set of national standards that are expressed in RDF. It's SKOS for concepts and terms. It's DCAT for data catalogs and it's CPSV for core public services and to be able to describe them. And it's a demand for the public sector to comply to those. And when they have data in Databricks, for example, how can we connect to these national standards or to our internal ontologies with the data in Databricks to make the ontologies operational?

Veronika:
So that's a use case that I stumble across a lot lately. And I've actually written about this recently because I did a teeny tiny project on that at the Culture Heritage Directorate in Norway. And that again, it's like four lines of Python inside Databricks and you have your ontology operational on your data.

Larry:
Interesting.

Joe Reis

When Gartner declared 2026 "The Year of Context," Joe Reis leapt into action, immediately writing a good-natured satirical article about "context products," "context lakes," and the "analyst singularity."

It's a fun article that exemplifies Joe's no-nonsense approach to industry education and concludes with a serious point — "context does matter, and most organizations are terrible at it."

We talked about:

his forthcoming data modeling book, "Mixed Model Arts"
the origins his satirical post "Gartner declares 2026 the year of context"
our speculation on how the word "context" came to the fore
how his decades of experience help him fine-tune his hype detectors
"the one equals 10 dilemma" via which leaders extrapolate AI benefits that senior programmers gain onto less-skilled engineers
the challenges that executives miss of building a semantic layer
the endless quest for "silver bullets" over solving fundamental business problems
the relevance of Einstein's definition of stupidity in the AI hype cycle
how the big AI providers are like the ISPs of the 1990s
how generative AI has accelerated and improved his workflows
the trepidation around AI that he feels when he visits Silicon Valley and San Francisco
the unprecedented pace and scale and context of the current AI hype cycle
the role of the knowledge community in the current tech environment

Joe's bio
Joe Reis, a "recovering data scientist" with 20 years in the data industry, is the co-author of the best-selling O'Reilly book, "Fundamentals of Data Engineering." He’s also the instructor for the wildly popular Data Engineering Professional Certificate on Coursera, in partnership with DeepLearning.ai and AWS.

Joe’s extensive experience encompasses data engineering, data architecture, machine learning, and more. He regularly keynotes major data conferences globally, advises and invests in innovative data product companies, writes at Practical Data Modeling and his personal blog and hosts the popular data podcast "The Joe Reis Show." In his free time, Joe is dedicated to writing new books and articles and thinking of ways to advance the data industry.
Connect with Joe online

JoeReis.xyz

Joe's writing and podcast

Gartner Declares 2026 The Year of Context™: Everything You Know Is Now a Context Product
Fundamentals of Data Engineering (O'Reilly), Joe's bestselling book
Practical Data Modeling
Personal Blog
The Joe Reis Show

Video
Here’s the video version of our conversation:

https://www.youtube.com/watch?v=6A_FWL0hbKM



Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 47. When Gartner recently declared 2026 "The Year of Context," the gauges on Joe Reis' industry hype dashboard maxed out. Joe's a respected veteran of the data profession, known for his best-selling book, Fundamentals of Data Engineering, and for his courses, newsletters, conference keynotes — and especially for his no-nonsense takes on industry trends. He's also a good friend of the knowledge graph community. "Context" is just his latest tech-industry hype take-down.
Interview transcript
Larry:
Hi, everyone. Welcome to episode number 47 of the Knowledge Graph Insights Podcast. I am really delighted today to welcome to the show Joe Reis. Joe is a well-known figure in the data engineering and data world. He's the co-author of the book, Fundamentals of Data Engineering, which is kind of a category-setting book. He's working on a new book called Mixed Model Arts, on data modeling, and does a lot of other interesting stuff. He's really well known in the conference community. And anyhow, welcome to the show, Joe. Tell the folks a little bit more about what you're up to these days.

Joe:
Hey, what's up, Larry? What have I been up to lately? Just been editing Mixed Model Arts. I just actually finished, I guess, the main edits and just down to the very minor tweaks as of today. So that's awesome. So literally just working on that before we hopped on and I'll be working on that after we're done.

Larry:
Okay, Great. Well, sorry to interrupt your book. I'm a former book editor, so I always feel bad when I interrupt progress like that. Congrats.

Joe:
It's okay. Thank you.

Larry:
Do you have a publisher for the book?

Joe:
That would be yours truly, yes.

Larry:
All right. Okay. Well, anyhow, we'll keep the webpage-

Joe:
We'll talk about that later. Yep.

Larry:
Yeah, with info about where to get it. Well, hey, the reason this conversation came together, there was this great little convergence of meeting of ideas a couple of weeks ago. I had just done a presentation where I was talking about how hyped the AI cycle is. And then in quick succession, I saw a post from Juan Sequeda where he talked about some folks have mixed feelings about Gartner. And then I came across this post you had done, "Gartner declares 2026, the year of context." It was this brilliant satirical piece. Can you talk a little bit about that and what motivated it and just maybe a quick outline for folks?

Joe:
Yeah, I mean, I think spawned from... I guess my social media circles were like Gartner, and all of a sudden I started seeing my LinkedIn feed bombarded with the word context and how Gartner declares this the year of context and... I can swear in your show, right?

Larry:
Yeah.

Joe:
Okay, shit.

Larry:
It's fairly family friendly, but yeah.

Joe:
Yeah, it's all good. So I've seen them and similar research firms in the past declare this, that, or the other thing. And I just felt like this in particular seemed... And no offense to the knowledge graph folks there, whatever, you're all great. And I think it serves knowledge graph community really well, but the year of context I think is jumping in the gun a bit too fast. Where last year was a year of agents, year before that was year of AI or whatever, and it just seems like... It's what I described as the buzzword industrial complex where we jump... Not we, but certain groups in the industry need something new to push onto people in order to keep, I guess, discussions going, in order to keep people attending conferences, in order to keep selling consulting services and all this other stuff.

Joe:
And so I felt like this was really just another instance of it, but I decided that I had had a few spare cycles in between editing my book. So I was like, "Oh, let's just write a satirical piece on this," maybe somewhat satirical, maybe just kind of poking fun at just, I guess, the nonsense of the industry that we keep finding ourselves in over and over again. So that was all there was to it, Larry.

Larry:
Okay. Well, one of the ways you contextualize that was this, I forget what you call it, the conference content capital cycle, this self-reinforcing loop, which appeared to me to mirror this kind of whatever that bizarre financial loop that's keeping the AI companies up. Was that intentional or was I just reading into that?

Joe:
I mean, I don't know if it was intentional, but it's just an observation that I've noticed in that article, and I think a few others, where it was very much... It's a self-sustaining thing where you need the news story, you need this. And it's the same as the AI hype cycle right now where it's just a very circular system. And so just that the money just sort of rotates around and that's just kind of how it is amongst strangely a lot of the same players, which I think is kind of funny.

Larry:
Interesting. Yeah, so maybe we've just stumbled upon some universal dynamic that drives various kinds of hype cycles. But one thing that occurred to me is there's always some fundamental underlying, it's business anxiety or truth or something like that that's driving these things. The context thing, do you have any hunch where that came from? I remember it just hit my LinkedIn feed, what, three or four months ago and it's been constant ever since.

Joe:
I'll ask you this actually. I mean, let me reverse the roles of a host and guest here. I mean, you've been in the knowledge space for a while and I imagine that some manifestation of the word context has come up in your discussions with your peers. So I guess if I'm in your shoes and those of your peers, what's it like to see a word like context or semantics or ontology or graphs becoming these sort of terms du jour?

Larry:
Well, in one sense, it's really gratifying, of course, because we're on the radar screen. You can actually say ontology in public now, which has not been the case for the last 10 years.

Joe:
Yeah, you get jailed for doing that. Yeah.

Larry:
Exactly, yeah. Put you in the stocks in the middle of the courtyard. But no, so it's really interesting. And that's one of the reasons I'm curious about your take on it, because it's like there's these real things that drive it. But in terms specifically of context, I was just reminded just of... Somebody on LinkedIn today just shared a post I did recently about Dave McComb's... I don't want to get too nerdy, but this is a Knowledge Graph Insights podcast, so I'll set a little context. There's this thing in knowledge graph construction. You have the A box, the assertion box, which is like all the things, all the data instances that are in there. Then you have above that, you have the T box, which is the concepts that describe it, the ontology basically, typically.
Dave McComb, who I think you must know, because the data centric enterprise and all that.

Joe:
Mm-hmm.

Larry:
He articulated this notion, I don't know, a couple of years ago of the CBox. And what was really interesting in this post I saw today is that he used it as the categorization box. That's where you put all the taxonomic terms, vocabularies, all that sort of what I think of as the metadata about the data is sort of in there. And I didn't realize at the time,

Robert Sanderson

Yale University manages huge collections of precious cultural heritage artifacts housed in multiple museums, libraries, and other collections.

Using knowledge graph and ontology engineering design patterns that he has developed over his career, Robert Sanderson helps scholars, researchers, and the general public access information about — and make connections across — millions of unique items in Yale's collections

We talked about:

his work as Senior Director for Digital Cultural Heritage at Yale University
the knowledge graph and ontology engineering design patterns that guide his work
the scope of his work — improving discoverability of Yale's extensive collections of artifacts, facilitating the management of collection information, and even collecting data on physical artifact storage facilities
how their linked data approach lets researchers easily connect information about artifacts and information housed in multiple museums, libraries, and collections
how the growth of LLMs has affected their KG user interfaces
how AI is accelerating their ability to add to their knowledge graph the millions of artifacts in their collections that aren't yet accounted for
the compact nature of their three-billion-triple KG ontology, just 10 classes and 50 relationships
the extensive vocabularies and taxonomies they use
how they handle the need to reconcile the identity of lesser-known people who don't have a Wikipedia page or other authoritative references available
how they balance the competing needs of comprehensiveness and usability as they build their knowledge graph
how knowledge graphs facilitate discoveries that other search tools can't
current opportunities for post-docs to join his team to work on leading-edge AI projects

Robert's bio
Dr. Robert Sanderson is the Senior Director for Digital Cultural Heritage at Yale University, where he works with the libraries, archives, and museums to ensure that data and other digital efforts are coherent and connected. He is the principal architect for Yale’s cross-collection discovery system, LUX, which is built on the Linked Art specifications, for which he is an editor. He is also an editor for the IIIF specifications, was the co-chair and editor for JSON-LD and the Web Annotation data model in the W3C. He has previously worked at the Getty in Los Angeles, Stanford University, Los Alamos National Laboratory, and the University of Liverpool. His current areas of work and research are at the intersections of cultural heritage, knowledge graphs, data usability, and generative AI.
Connect with Rob online

LinkedIn
email: robert dot sanderson at yale dot edu

Rob's LinkedIn post series on KG and ontology design patterns

The 10 Design Principles to Live By
Ontology Design Patterns
Naming Things
Avoiding Reification
Foundational Ontologies
Multiple Inheritance, Not Multiple Instantiation
Predicate Reuse... Meh
Document your ABCs
Separate Query and Description Semantics
Usable vs Complete
acknowledgements

Video
Here’s the video version of our conversation:

https://youtu.be/SMAVyrL3aSU
Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 46. When your job is to help scholars and the public discover information about millions of cultural heritage artifacts that are housed in multiple museums, libraries, and other collections, you need a powerful — but also manageable — knowledge graph. That's Rob Sanderson's role at Yale University. He and his team apply time-tested ontology and knowledge engineering design patterns to help people discover — and see the connections between — these precious human artifacts.
Interview transcript
Larry:
Hi everyone. Welcome to episode number 46 of the Knowledge Graph Insights Podcast. I am really delighted today to welcome to the show Robert Sanderson. Rob is a professor and the senior director of Digital Cultural Heritage at Yale University, the Ivy League School in Connecticut. Welcome to the show, Rob. Tell the folks a little bit more about what you're up to these days.

Rob:
Hi, Larry. Thank you so much for inviting me to be part of the illustrious lineup of guests on your podcast. So yeah, I'm Rob Sanderson, as you said, Senior Director for Digital Cultural Heritage at Yale. So I work with the libraries, the archives, and the museums and other collecting organizations at Yale to help them to be more connected with linked data organizationally and more coherent in the way that we do things digitally. So our projects really focus on discovery and access to the collections in service of the university mission, which of course is teaching and learning, research, and preparing our students to be the next generation of leaders in the world.

Rob:
So for that, the university invests very heavily in the collections, which is fantastic. We are super proud of the 300 years of collecting that we've done. But we want to make sure that if you can't come to New Haven, you still have as good access to those collections as possible. And the ability to find amongst the many millions of objects that we steward exactly what it is that you need. So a lot of our projects focus on describing the collections in a more computationally tractable way so that that discovery can be better. And also how to manage the information that's associated with the collection, but isn't a museum object or a archival object itself. For example, I have two postdocs that are openly available. So if you are a few years out of your PhD or just about to graduate, do get in touch to work on how to use AI to extract the ownership history or the provenance of particular museum objects from the archival content that we also manage. Equally, how can we align research data sets with the collections? So we also have a natural history museum as well as two art museums. How can we align the environmental datasets that are out there on the web with the natural history specimens that could have been impacted by those environments?

Rob:
Yeah. And then equally, we look at the environment of Yale. So we have a large project at the moment to set up environmental monitoring with sensors for light, for humidity, temperature, and so on, to be able to generate a large data warehouse aligned with linked data with the collections so that we can have evidence of what the effects of the environment are on the collection items themselves.

Larry:
Interesting. That is so fascinating. What a fascinating remit. One quick thing about what you just said. Is that about humidity and temperature and all the things that might affect the endurance of these physical artifacts?

Rob:
Yep. Yes. That's right.

Larry:
Yeah.

Rob:
We have about 200 sensors around the place monitoring every five minutes a new data point, which if you think about it, it's actually not that much data.

Larry:
Yeah. I have to say, I just love that you're doing data stuff along with it. That you're not just sitting in a dusty old room collecting things. You're doing cool modern stuff too. But hey, I want to quickly interject how we met, and I just want to put this in because we won't have time to talk about it today, but I want people to know about this fantastic series you did. That's how we met was somebody drew to my attention the series you've done on ontology design and on knowledge engineering design patterns. And I'll point to that in the show notes, but I just wanted to mention. And the more I think about what you just said, because I didn't know all of this background before we started recording, I'm like, "Oh, this is even better than I thought." So I'll point to that in the show notes.

Larry:
But the main thing I wanted to talk about today is what you were just talking about. This amazing cultural heritage operation that you're running there, especially the knowledge graph component of it and the AI, of course, because we're in the 21st century, and that's all anybody talks about. One of the things we talked about before we went on the air was how AI is accelerating the ability for you to build your knowledge graphs of these cultural heritage artifacts and data. Can you talk a little bit about that, how AI is helping in that?

Rob:
Yeah. Of course. Absolutely. So just a little bit of a background about the knowledge graph itself first before I get to the AI part. So over the past five years, we've built without AI, a very large scale knowledge graph, well, in cultural heritage terms of very large scale, which has about three billion triples in it. And it follows the principles and the design patterns that you mentioned in those posts on Linked Art. It then aligns the people, places, concepts, events, objects, works, collections that we manage here at Yale across the two art museums, Natural History Museum, the dozen or so libraries. There's also a collection of musical instruments, the Institute for the Preservation of Cultural Heritage, and we even have a little outpost in London, in England for art history research that we include. So that work uses the linked art ontology, which is based on the foundational site CRM ontology and is publicly available both in terms of the data, you can just download it. But also in terms of the graph queries, we don't force you to learn SPARQL. We have a user interface on top of it, which allows you to generate queries and find the objects that you are looking for.

Rob:
So one of the things that we noticed first about the user interface is that only about 5% of searches are actually using the graph affordances. Mostly, 95% of the time, people just put in keywords because that's what they're used to. You go to Google, you type in your five favorite keywords that you think might match and you scroll through the results. However, now in 2026,

Max Gärber

The promise of agentic AI is being realized in systems like the Service Copilot that Zeiss microscopes provides for its field service engineers.

The system integrates technical documentation, subject matter expertise, and user-generated insights which are orchestrated and shared with a suite of AI agents.

While it relies heavily on modern LLM technology, it's the system's solid knowledge graph and metadata foundation that make it a success.

We talked about:

Max's work "turning information into value" at PANTOPIX, a technical documentation and information processes consultancy based in Germany
a recent client project working with Zeiss to help their field service engineers operate more efficiently
how their prior knowledge management and machine learning work helped them not only cope, but thrive, at the arrival of ChatGPT and LLMs
the immediate positive stakeholder feedback they received as they incorporated LLMs into their knowledge architecture
how they extended the iiRDS standard with a custom ontology and taxonomies and integrated topic mappings into their system and workflows
an overview of the system architecture and tooling, which includes both a graph database and a vector store, an ontology and taxonomy management tool, and documentation of best practices
their evolution from simple prompt engineering and RAG approach to an agentic orchestration architecture
a few of the agents in their architecture:

a planning agent that organizes and orchestrates
a content agent that replaces the original RAG system
a troubleshooting agent which surfaces past solutions


the good problem they experienced of managing enthusiastic user adoption of the new system
the unexpected benefits to the Zeiss sales team of the system
how subject matter expertise, user generated content, and other insights are captured and used
the crucial role of knowledge management practices, structured content, and semantic technology in building the foundation for an organization's AI capabilities

Max's bio
Maximilian Gärber is Partner and Principal Technical Consultant at PANTOPIX. Max has been working in the field of technical communication for over 15 years.

As a Partner and Technical Consultant at PANTOPIX, he is responsible for the technical consultation and implementation of projects. In addition to project management, Max is responsible for data modelling and process optimization in relation to product information (migration, publication, translation) and product catalogues. He is also responsible for product development and ensures that innovative solutions for our customers are continuously developed and optimized.
Connect with Max online

LinkedIn
PANTOPIX

Resources mentioned in this episode

Industrial Knowledge Graph meets Agentic AI: Service Copilot at ZEISS RMS slide deck
Service Copilot from ZEISS article

Video
Here’s the video version of our conversation:

https://www.youtube.com/embed/ttQOHvvxPyw
Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 45. When you're a field service engineer dealing with both the typical challenges of information overload and the need to maintain complex machinery like a high-end Zeiss microscope, you'd really benefit from an intelligent knowledge management system, one that integrates technical documentation, subject matter expertise, and user-generated insights. That's exactly what Max Gärber has built - an agentic AI system grounded in a solid knowledge graph foundation.
Interview transcript
Larry:
Hi everyone. Welcome to episode number 45 of the Knowledge Graph Insights podcast. I am really excited today to welcome to the show Max Garber. Max did a really interesting presentation at the Semantics conference in Vienna last fall, and I've been trying to get him on the show ever since. So here he is. I'm excited to have him here. Max, he's a partner and a technical consultant at PANTOPIX, a consultancy based here in Germany. Welcome, Max. Tell the folks a little bit more about what you're doing these days.

Max:
Yeah, thanks Larry. Thanks for having me. Yeah, great show. And yeah, we are mostly concerned with helping mainly our industrial customers structure their content and integrate it from various sources into their systems, delivery systems, wherever it is needed. So yeah, it's mainly consultancy on data modeling, on how to do information processes and how to get the best out of your data, so to say. So our mission here is literally turning information into value.

Larry:
Oh, I love that. That's a great tagline for a consultancy. Well, you did the use case, the case study you talked about in Vienna was really interesting to me. This issue of Zeiss microscopes, in particular their research microscopy solutions arm, which is these big, expensive, complex machines that require a lot of service. Can you talk a little bit about how you got involved with Zeiss and what you do to help them? In particular, the thing you talked about in Vienna was about the system to help their field service engineers. Can you talk a little bit about that project?

Max:
Yeah, exactly. The main objective there was helping the field service engineer to get the information in that situation when they need it and in the format they need it. That is essentially the bottom line of it. And it started essentially as a knowledge management project. Zeiss, RMS, they have been really into structuring, getting structured content, adding proper metadata to it so it can be used in various cases. The idea has been to integrate from various sources, spare part system, for example, or the manuals from the technical documentation or ticket information and get them into one system so there's a single point of access for the service technicians. So they don't need to spend a lot of time in all of the different systems that there are to get the information about that case they are currently working on because there's a lot they need to consider when servicing or troubleshooting a microscope.

Max:
And yeah, that project evolved into what is now the Service Copilot because I think it was in early '22 when we started the project. And one part of it was to not only integrate all of that information in one place, but also recommend content to the service technician. So, if you were working on a specific case, so the ticket was known, the product was known, you should get a recommendation of articles, "Hey, this is how you install this and that component," for example. So we actually worked a lot on labeling tickets. We actually had a custom labeling interface and used, let's say, classical machine learning approaches to get that recommendations done.

Max:
And it worked not so good, but that was also the same time when GPT, I think it was 3.0 or 3.5 came out. And yeah, we were faced with that situation that there was a new technology available that looked like it could do everything and much more what we were currently doing without much effort. So we really faced the situation there to either stop the project or reinvent ourselves, I would say.

Larry:
I love that juncture. We were talking a little bit before we went on the air about you were really concerned at that point as this arose, but then it turns out that the prior work you had done, the knowledge management work you had done and the machine learning skills and workflows and things you developed, it turns out you ended up being, to my mind, it looks like from that demo I saw in Vienna, at the leading edge of hybrid AI architectures and agentic AI.

Max:
Yeah, I mean, totally. It evolved really quickly. At the point where we looked into GPT and what language models could do, we asked for, "Hey, can we do some quick prototyping research on this and see if we can replace, let's say, the machine learning pipeline that we had with language models?" And it worked really well from the start. So in the beginning, we had 15 service technicians as pilot users that were constantly evaluating the system and giving us feedback, "Hey, that's good, that's not good." And they said immediately, "Well, this is working really well." I mean, they tried, of course, at the very beginning to trick the system and ask the hard questions. And if you look at the content that they are provided, a service manual, it has hundreds of pages and the products that they are servicing, they look quite similar, but they are quite different.

Max:
So there's a lot of variants in what components you can use, how you configure the system, how you buy it. So it's really important that if you have a certain product variant, you don't mix that up. And if you look at how the content is, it is very similar. So of course they have the same structure or a very similar structure and certain, let's say, chapters or topics, they are always very similar. So how you install electron microscope A is very similar to how you install electron microscope B, but it's the little differences that are really important if you are doing that installation procedure. If you forget one of those steps, of course, you will fail or you could even do some harm to the system. So it's really important that you not only have similar content or similarity in, let's say, the retrieval of the content, but you can actually know, "This is content for product A and this is content for product B."

Max:
So all of the work that went into structuring the content, adding metadata to each of the topics and connecting the metadata based on what entities are linkable, the RAG system that we implemented then, it could actually filter out all of the content that was not relevant to the specific question or use case. So the answers were quite good from the beginning.

Larry:
Yeah. I want to elaborate a bit on the evolution of your RAG architecture, and for folks who don't...

Quentin Reul

The complementary nature of knowledge graphs and LLMs has become clear, and long-time knowledge engineering professionals like Quentin Reul now routinely combine them in hybrid neuro-symbolic AI systems.

While it's tempting to get caught up in the details of rapidly advancing AI technology, Quentin emphasizes the importance of always staying focused on the business problems your systems are solving.

We talked about:

his extensive background in semantic technologies, dating back to the early 2000s
his contribution to the SKOS standard
an overview of the strengths and weaknesses of LLMs
the importance of entity resolution, especially when working with the general information that LLMs are trained on
how LLMs accelerate knowledge graph creation and population
his take on the scope of symbolic AI, in which he includes expert systems and rule-based systems
his approach to architecting neuro-symbolic systems, which always starts with, and stays focused on, the business problem he's trying to solve
his advice to avoid the temptation to start projects with technology, and instead always focus on the problems you're solving
the importance of staying abreast of technology developments so that you're always able to craft the most efficient solutions

Quentin's bio
Dr. Quentin Reul is an AI Strategy & Innovation Executive who bridges the gap between high-level business goals and deep technical implementation. As a Director of AI Strategy & Solutions at expert.ai, he specializes in the convergence of Generative AI, Knowledge Graphs, and Agentic Workflows. His focus is moving companies beyond "PoC Purgatory" into production-grade systems that deliver measurable ROI.

Unlike traditional strategists, he remains deeply hands-on, continuously prototyping with emerging AI research to stress-test its real-world impact. He doesn't just advocate for AI; he builds the technical roadmaps that translate the latest lab breakthroughs into safe, scalable, and high-value enterprise solutions.
Connect with Quentin online

LinkedIn
BlueSky
YouTube
Medium

Video
Here’s the video version of our conversation:

https://youtu.be/J8fgIezoNxE
Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 44. We're far enough along now in the development of both generative AI learning models and symbolic AI technology like knowledge graphs to see the strengths and weaknesses of each. Quentin Reul has worked with both technologies, and the technologies that preceded them, for many years. He now builds systems that combine the best of both types of AI to deliver solutions that make it easier for people to discover and explore the knowledge and information that they need.
Interview transcript
Larry:
Hi, everyone. Welcome to episode number 44 of the Knowledge Graph Insights podcast. I am really delighted today to welcome to the show Quentin Reul. Quentin is the director of AI Strategy and solutions at expert.ai in the US in Chicago. So welcome, Quentin. Tell the folks a little bit more about what you're up to these days.

Quentin:
Hi, thank you, Larry, for accepting me and getting me on your podcast. So my name is Quentin Reul. I actually have been around the RDF and the knowledge graph since before it was cool in the early 2000. And today, what I'm helping people in news, media, and entertainment is to see how they can leverage all of the unstructured data that they have and make it in a way that can be structured and they can make their content more findable and discoverable as part of what they are offering to their customers.

Larry:
Nice. And I love that you've been doing this forever. And one of the things we talked about before we went on the air was your early involvement in the SKOS standard. Can you talk a little bit about your little contribution to that project?

Quentin:
Yeah. So for this, we do know what SKOS stands for Simple Knowledge Organization System. It's a standard that has been created by the W3C standard around 2005. And being at the University of Aberdeen in Scotland, we had a lot of involvement with the W3C voicing the web ontology language and SKOS.

Quentin:
For SKOS, I was actually working on my PhD, and the idea of my PhD was to look at two ontologies and trying to map entities from one ontology to the entities in the other one. And a lot of the approach that were taken at the time were either leveraging philosophical kind of representation. And there was not really a lot of things that were looking at linguistics. So the approach that we were taking was looking at WordNet and using the structure of WordNet and maps that to the linguistic information, so the labels that were associated with nodes in the taxonomy.

Quentin:
But to do that, we needed to have a structure that was transitive. And at the time, SKOS only had broader and narrower, and they didn't have the transitive property. So my contribution was to push for the W3C standard and SKOS to include the SKOS broaderTransitive and SKOS narrowerTransitive, so that I could now have that if A broader B and B broader C, that A broader C was also correct, and having that description logic structure that would enable that.

Larry:
Well, that's so cool. I love that you have your ideas are ensconced in this 20-year-old standard now. But hey, what I wanted to talk about today and really focus on, I know I was excited to get you on the show because you're doing a lot of work in the area of neuro-symbolic AI, the idea of integrating LLMs and other machine learning technologies with knowledge graphs and other symbolic AI stuff.

Larry:
It's one of those things that everybody's talking about, but I haven't had the chance to talk on the podcast with many people who are actually doing it. So I'm hoping that you can help the listeners take the leap from this conceptual understanding of the natural complimentary nature of them to actually putting them together in an enterprise architecture. I guess maybe start with the strengths and weaknesses of each of the kinds of AI that we're talking about here.

Quentin:
Yeah. So if we look at the history of AI, symbolic AI was a thing that came up in the '70s and led to the first AI winter and the second AI winter for that matter. But where they were very good was in the structure and the explainability. So if you aren't very well set set of rules or predictive kind of aspect, it would do it consistently, repeatably, and all of that type of things.

Quentin:
Now, when you were trying to adopt a rule-based system for new data, it would die off because you had never seen that or a new set of rules or a new set of business requirements, it would just not handle that. And that's where machine learning really helped in making that transition to where we are today.

Quentin:
And the LLM, contributing further to that, in as much as the machine learning was pretty good at dealing with new patterns, as long as it was similar to the data that you were training with. I think one thing that the LLMs have really shine is in the way that it's able to surface things that you were not predicting from the data.

Quentin:
One thing that I think that we could have predicted or seen from the data if we had LLMs back in 2020 is we could probably have seen the topic of COVID emerging a bit earlier than what it did. And the reason is, it's because it's very good at surfacing things that it's never seen before. It's able at interpreting the language and analyzing the language in its structure. And by the sentence structure, understanding that things are very similar, and you may use different words for them, but now you're able to interpret them.

Quentin:
So if we think about information retrieval in the '90s, 2000s, and even in the 2010s, the way that we were doing a lot of these things was using control vocabulary, CISORI, or other dictionaries, and they were used to do query expansion. So you add a keyword, you were looking in the dictionaries, the dictionary were doing an expansion, and then you add something else.

Quentin:
Well, now with the LLM, that kind of expansion is intuitive to the actual LLM because you had seen so many different aspect and so many occurrence of text that it can actually predict and see what these different terms are associated with a holistic concept.

Quentin:
Now, that's a good thing. On the bad thing, the LLMs don't have ... Well, they have a cutoff point or knowledge cutoff point, which means that when they are trained, they are trained of information that is in the past. So they're not always that great at predicting, especially current event or information about things that are happening today, they're not very good at that.

Quentin:
I think if I look at the data, generally between the release of a new model and the nature of the data or the cutoff point, it's about six months to a year. This is like going a bit slower now or shorter in terms, but you have to remember that the time that it takes to train these models, we're speaking about days, weeks, and sometime months as opposed to hours with machine learning models. So they're expensive as well from that perspective.

Quentin:
Another aspect that they don't have, it's a knowledge base to just take a higher level from a knowledge graph, like the knowledge base. So it's not able to disambiguate information in a large corpus. It's very good to do entity linking within the context of one document.

Quentin:
So if you pass it one document, let's say a financial document, and it refers to Acme as an enterprise, if Acme is mentioned several times during the document, it will infer that there is only one entity and that entity is Acme.

Quentin:
But now, imagine that you have a group of financial reports, and these financial reports refer to Acme, a bakery in Illinois, and Acme, a construction company in Maryland.