Top insights from Knowledge Graph Insights

A presentation at World IA Day London 2026 in March 2026 in London, UK by London World IA Day

Slide 1

Slide 1

Top insights from Knowledge Graph Insights Larry Swanson, Content architect, podcast host, community event organiser London 2026 #Designing4Meaning #wiad26

Slide 2

Slide 2

Top 10 Knowledge Graph Insights Take-home lessons from 45 podcast interviews and 6 years of immersion in the semantic technology community Larry Swanson, WIAD London, 10 March 2026

Slide 3

Slide 3

1

Slide 4

Slide 4

  1. At first glance, knowledge graphs and LLMs seem totally at odds with one another.

Slide 5

Slide 5

  1. But if you think about how human’s process information, it becomes clear that you need at least two kinds of thinking.

Slide 6

Slide 6

  1. So in the same way that contrasting fundamental properties contribute to a holistic human mindset and approach…

Slide 7

Slide 7

  1. …hybrid AI architectures get closer to the innate cognitive awesomeness that drives human intelligence.

Slide 8

Slide 8

  1. KGs and LLMs complement each other AI systems benefit from both learning systems and knowledge systems, and from both general and domain-specific information. Machine Learning Knowledge Representation

Slide 9

Slide 9

2

Slide 10

Slide 10

  1. When you first discover a new technology, it’s tempting to use it everywhere…

Slide 11

Slide 11

  1. …especially if you’ve devoted a good part of your life to understanding and applying it.

Slide 12

Slide 12

  1. But your CEO doesn’t care about your cool craft or your carefully developed practice expertise…

Slide 13

Slide 13

  1. …they just want to see business outcomes that support their need to grow the bottom line and keep their board happy.

Slide 14

Slide 14

  1. Always focus on a business problem Ground your work in a clearly understood problem space that addresses a real and measurable business problem.

Slide 15

Slide 15

3

Slide 16

Slide 16

  1. Many engineers and business people regard the “semantic web” as a hippie dream that failed.

Slide 17

Slide 17

  1. In fact, semantic web technologies appear in more than half of the web pages on the internet…

Slide 18

Slide 18

  1. …and virtually every major technology company uses semantic web technology behind the scenes…

Slide 19

Slide 19

  1. …and traditional industries like media, financial services, pharma, energy, and others use knowledge graphs extensively.

Slide 20

Slide 20

  1. The Semantic Web is alive and well The Semantic Web is “the most catastrophically successful thing which people have called a failure.”

Slide 21

Slide 21

4

Slide 22

Slide 22

  1. Enterprise systems, including AI, benefit from semantically meaningful, diligently stewarded data and content…

Slide 23

Slide 23

  1. …but engineers too often work with hastily assembled databases full of vaguely labeled tables and messy data…

Slide 24

Slide 24

  1. …resulting in messy systems that address only narrow concerns and obscure business meaning.

Slide 25

Slide 25

  1. AI needs clean data and meaningful metadata If data is “the new oil,” then you need light sweet crude, not messy sludge, and it needs to be semantically understandable.

Slide 26

Slide 26

5

Slide 27

Slide 27

  1. Ontologists, especially enthusiastic newcomers, are sometimes tempted to overbuild knowledge graph models…

Slide 28

Slide 28

  1. …but semantic technology spans a whole spectrum of ways to add meaning to data.

Slide 29

Slide 29

  1. Know where you are on the semantic spectrum You don’t always need a full-blown, reasoning-capable ontology for your knowledge graph.

Slide 30

Slide 30

6

Slide 31

Slide 31

  1. People have always struggled to align with each other on fundamental questions like what things are…

Slide 32

Slide 32

  1. …and we’re notoriously bad at communicating what we mean to say and how we understand each other.

Slide 33

Slide 33

  1. Even the main word we use to describe these attempts has been demoted to a trite, rhetorical truism.

Slide 34

Slide 34

  1. Getting people to agree on meaning is hard The biggest bottleneck in knowledge work is not technology, but rather the need for clear communication and human agreement.

Slide 35

Slide 35

7

Slide 36

Slide 36

  1. Business activities tend to happen in silos, resulting in data practices that hinder enterprise understanding.

Slide 37

Slide 37

  1. When marketing, sales, accounting, HR, and operations each use a different word to describe a “customer,” meaning is lost…

Slide 38

Slide 38

  1. …and opportunities are squandered as those language differences are captured in enterprise systems…

Slide 39

Slide 39

  1. …when with a more broadly informed and conceptually connected view they could see that they’re talking about the same thing. Semantic Layer

Slide 40

Slide 40

  1. Silos hide connections — KGs reveal them Understanding data independent of its isolated use in any one silo can can unlock hidden business treasures.

Slide 41

Slide 41

8

Slide 42

Slide 42

  1. It’s tempting to think of knowledge graphs as just another technology…

Slide 43

Slide 43

  1. …but the practices that make up ontology design and knowledge engineering trace their origins to well before the computer age.

Slide 44

Slide 44

  1. The ontology principles that capture shared human understanding of a domain come from the metaphysics branch of philosophy.

Slide 45

Slide 45

  1. And the logic that undergirds the powerful reasoning capabilities of knowledge graphs also comes directly from philosophy.

Slide 46

Slide 46

  1. The organisation and labelling schemes that facilitate discovery of knowledge artefacts trace their origins to library science.

Slide 47

Slide 47

  1. And the field of symbolic AI to which knowledge graphs belong traces its roots back to linguistics concepts like the semiotic triangle. Thought or Reference s e z i l o b m y s Symbol re Semiotic Triangle stands for fe rs to Referent

Slide 48

Slide 48

  1. KGs are grounded in the humanities While they are expressed in technical systems, knowledge graphs are built on a foundation of centuries-old human wisdom.

Slide 49

Slide 49

9

Slide 50

Slide 50

  1. Historically, it has been difficult to build ontologies and taxonomies and to populate them with instances and examples.

Slide 51

Slide 51

  1. The arrival of LLMs accelerates once-burdensome tasks like entity extraction, the process of identifying entities in documents…

Slide 52

Slide 52

  1. …and taxonomy construction, the practice of organising terms and concepts into hieararchical classification schemes.

Slide 53

Slide 53

  1. The extracted terms and draft taxonomies still need human oversight, but tasks that once took weeks now take just hours.

Slide 54

Slide 54

  1. LLMs facilitate knowledge graph building Many tedious ontology design and semantic engineering tasks are now assisted and accelerated with LLMs.

Slide 55

Slide 55

10

Slide 56

Slide 56

  1. As the Silicon Valley hype machine puts up billboards touting human-free workplaces… SV “replace people” ad

Slide 57

Slide 57

  1. …humans remain as relevant as ever, providing the leadership that computer systems need.

Slide 58

Slide 58

  1. Put humans in control, not just in the loop As Yaakov Belch said in our conversation, forget about “human in the loop” - let’s put “humans in control.”

Slide 59

Slide 59

Top 10 Knowledge Graph Insights 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. KGs and LLMs complement each other Always focus on a business problem The Semantic Web is alive and well AI needs clean data and meaningful metadata Know where you are on the semantic spectrum Getting people to agree on meaning is hard Silos hide connections — KGs reveal them KGs are grounded in the humanities LLMs facilitate knowledge graph building Put humans in control, not just in the loop

Slide 60

Slide 60

Thank you! /LarrySwanson LarrySwanson.com