Exploring the Complexity of Graph Models: RDF vs Property Graphs

Ashleigh Faith With her 15-year history in the knowledge graph industry and her popular YouTube channel, Ashleigh Faith has informed and inspired a generation of graph practitioners and enthusiasts. She's an expert on semantic modeling, knowledge graph construction, and AI architectures and talks about those concepts in ways that resonate both with her colleagues and with newcomers to the field. We talked about: her popular IsA DataThing YouTube channel the crucial role of accurately modeling actual facts in semantic practice and AI architectures her appreciation of the role of knowledge graphs in aligning people in large organizations around concepts and the various words that describe them the importance of staying focused on the business case for knowledge graph work, which has become both more important with the arrival of LLMs and generative AI the emergence of more intuitive "talk to your graph" interfaces some of her checklist items for onboarding aspiring knowledge graph engineers how to decide whether to use a property graph or a knowledge graph, or both her hope that more RDF graph vendors will offer a free tier so that people can more easily experiment with them approaches to AI architecture orchestration the enduring importance of understanding how information retrieval works Ashleigh's bio Ashleigh Faith has her PhD in Advanced Semantics and over 15 years of experience working on graph solutions across the STEM, government, and finance industries. Outside of her day-job, she is the Founder and host of the IsA DataThing YouTube channel and podcast where she tries to demystify the graph space. Connect with Ashleigh online LinkedIn IsA DataThing YouTube channel Video Here’s the video version of our conversation: https://youtu.be/eMqLydDu6oY Podcast intro transcript This is the Knowledge Graph Insights podcast, episode number 24. One way to understand the entity resolution capabilities of knowledge graphs is to picture on old-fashioned telephone operator moving plugs around a switchboard to make the right connections. Early in her career, that's one way that Ashleigh Faith saw the power of knowledge graphs. She has since developed sophisticated approaches to knowledge graph construction, semantic modeling, and AI architectures and shares her deeply informed insights on her popular YouTube channel. Interview transcript Larry: Hi, everyone. Welcome to episode number 24 of the Knowledge Graph Insights Podcast. I am super extra delighted today to welcome to the show Ashleigh Faith. Ashleigh is the host of the awesome YouTube channel IsA DataThing, which has thousands of subscribers, thousands of monthly views. I think it's many people's entry point into the knowledge graph world. Welcome, Ashleigh. Great to have you here. Tell the folks a little bit more about what you're up to these days. Ashleigh: Thanks, Larry. I've known you for quite some time. I'm really excited to be here today. What about me? I do a lot of semantic and AI stuff for my day job. But yeah, I think my main passion is also helping others get involved, understand some of the concepts a little bit better for the semantic space and now the neuro-symbolic AI. That's AI and knowledge graphs coming together. That is quite a hot topic right now, so lots and lots of untapped potential in what we can talk about. I do most of that on my channel. Larry: Yeah. I will refer people to your channel because we've got only a half-hour today. It's ridiculous. Ashleigh: Yeah. Larry: We just talked for an hour before we went on the air. It's ridiculous. What I'd really like to focus on today is the first stage in any of this, the first step in any of these knowledge graph implementations or any of this stuff is modeling. I think about it from a designerly perspective. I do a lot of mental model discernment, user research kind of stuff, and then conceptual modeling to agree on things. But when you get into this world, you get much more into the implementation side of going from a conceptual model into logical, physical models as well. Can you just talk a little bit first just about why modeling is so important? Ashleigh: Yeah. Modeling is the way that you put any of your data into context. If you're looking at something as a human and you see a column of names, you can look at that and say, "Oh, I see that as a human name." But you don't know if they're a customer, are they staff, are they vendors. You have no idea unless there's a column header that tells you what that is. That is the most simplistic model, it's a list. Ashleigh: That's why modeling is so important is because if you don't have any context to what this data is, and what it means, and how you should interpret it, it basically means nothing to you. Then you can misinterpret it and that leads to all kinds of problems. Larry: Right. One of the things we talked about before we went on the air was, "What are facts? What is knowledge?" Because ostensibly, that's what we're ensconcing in these systems that are built with these conceptual models that we come up with. How do you discern that stuff? Ashleigh: Yeah. If you look at a lot of us in the semantic space look a lot at Wikidata. If you look at Wiki data, these things are called statements. A triple that defines something and makes a statement about the world. In my mind, I come from a very deep scholarly community background where we're doing a lot of research and you're trying to find corroborating evidence. In my mind, when you turn a statement into a fact, it is when in that point in time, what is the overwhelming acceptance of a certain stance or statement in the world based on corroborating evidence. Now there are competing opinions about things. There are disputes, especially when you're talking about scholarship. Some people, their findings are one thing, and findings are different in a different study. Ashleigh: But all of that comes down to is there enough corroborating evidence in one direction? When there are disputes, sometimes there's nuance that has been added to the original statement where that original statement is still now true, it's still accepted. But now, with this additional evidence, it gets even more nuanced, so you get more specific. You can really understand the nuances of that. Ashleigh: There is a half-life of facts, though. Because there was a point in time in the world where people, an overwhelming amount of people, thought the world was flat. We all know that is not the case. But at the time, that was a fact because there was no other evidence to support it otherwise. Or there was very little, or it wasn't disseminated appropriately because it was quite some time ago. But that's where it all comes down is can you defend? If you're in a court of law, how do you defend your statements? How do you defend your argument? This is how scholarship has done things since the very beginning of time. Give me your evidence, go do some studies, and go and do some experiments to gather evidence to support your claim. That's what a hypothesis is doing, is can you support your hypothesis? Can you disclaim it? That's how you figure out what a statement and a fact is. Ashleigh: Then when you have that, how do you codify it so that it can be even more useful? That's where knowledge graphs really come in because you can create it in a way that you can do inferencing. I know that's a weighted statement nowadays. Unfortunately, it's a weighted statement. Oh, actually, even saying it's a weighted statement is problematic. I should stop while I'm ahead on that one. Larry: Yeah. Okay, we can change it. No. Ashleigh: Yeah. No, no. You can add in though that data governance aspect, especially if you're using an ontology. There's all these other aspects of why taking statements, and facts, and all of that evidence, and adding it into a system of record that you can then do other things with is really, really helpful, especially in this AI world. Larry: Yeah. That notion of system of record, for some people that's enterprise lingo. I love that you're talking about it. I love the academic and intellectual rigor that underlies your approach to modeling. I think a lot of the facts and knowledge that people are ensconcing in systems in the knowledge graph world, there's just a lot of enterprise stuff going on. What are the facts, and evidence, and corroboration that you need? Like the classic thing that comes up in every conversation. When you say "customer," what do you mean? Ashleigh: Yeah. Larry: How do you ensconce that organizational disparity in understanding of that term? Ashleigh: Oh, but that's why I love knowledge graphs for this! You can have your data catalog and you can have your taxonomies. You can attempt to get everyone in your organization to agree on what a specific label means. In my practical experience, all those things are great and lovely. And yes, do those if you can do do those. Often times though, and this is what I learned very early on in my career when I was first doing taxonomy work, was nobody ever agrees on what label is used for certain things. Or very few. There's always, "Well, there's that exception to the rule in our enterprise and it's super critical to our mission," and whatever else it might be. So you have that going on. Ashleigh: That's why I really love the very early examples where knowledge graph was used as a connector. I almost imagine it as those really old-school operators that would connect people with phone lines. You know, sitting there with the giant connector boards. That's what I think about when I think of the early examples that I was using with knowledge graph, which is you have a node and it represents this concept. That concept can be represented by an ID, so it does not need interpretation. It is that is the ID. That is the UID,