Lessons Learned from 25 Years in Semantics
KGC 2026
•
28m
"https://drive.google.com/file/d/1A4hiMKMIX6x1lrAintov1-Kf5ion4xcb/view?usp=share_link
Knowledge Graphs Are Not Enough. In this session, we’ll challenge the conventional wisdom around knowledge graphs. While they’ve been positioned as the cornerstone of enterprise semantics, they are not the end state.
They must continuously evolve to support the changing needs of modern organizations. A knowledge graph that isn’t mapped to enterprise data sources is effectively useless. Without mappings, it is just a model, not part of the business.
Drawing from 25 years of experience in semantics, we’ll explore:
● Why the knowledge graph is just one piece of the puzzle in creating a coordinated cognitive system.
● The shift from static ontologies to a dynamic context layer that ensures shared understanding across humans and AI agents.
● How the semantic layer enables humans and AI to reason together, bridging gaps in interpretation and operationalizing shared meaning.
● Why building and maintaining this semantic layer is no longer the sole domain of ontologists. You don’t need a special degree to contribute.
● Why AI lacks the contextual grounding needed for consistent reasoning and how a shared context layer closes that gap.
Join us to discover how agentic enterprise depends on a living context layer that evolves with your organization, ensuring alignment, coherence, and trust."
Up Next in KGC 2026
-
Taxonomy Design Best Practices
"https://drive.google.com/file/d/1x8vYa4d8CmunWXKRcCX1Exm6SczzRUe9/view?usp=share_link
Ontologies form the semantic framework for knowledge graphs, but to serve the purpose of connecting to content and standardizing metadata, ontologies need to be based on taxonomies and other controlled vocabul...
-
Using LLMs and Vectors for Knowledge ...
"This hands on workshop will provide an introduction to knowledge graph creation from unstructured (e.g. text documents) and structured data (e.g. CSV tables), retrieval augmented generation with knowledge graphs: aka GraphRAG.
- Into to GraphRAG concepts
- Build a knowledge graph from unstructu... -
Mastering maplib - a groundbreaking R...
maplib aims to be the go-to framework for handling and constructing RDF graphs in Python. It offers mapping with Reasonable Ontology Templates (OTTR), data frames, visual graph exploration, RDF store for queries, reasoning, validation, and even more! In other words, full support of semantic techn...
