Building Knowledge Graphs
summary
Knowledge graphs require cross‑discipline collaboration and combine technology, strategy and org change; they process 75–80% unstructured enterprise data (text, PDFs, audio) into subject‑predicate‑object triples, enable inference (RDF) versus traversal/analytics (LPG), and reduce LLM hallucination by validating outputs. Practical stack specifics: use Protege, ShEx, R2RDF for ontology, constraint and relational‑to‑RDF mapping, query with SPARQL, and deploy on a graph engine (Ontotext GraphDB is Ontotext GraphDB benchmark‑backed). Start small, import public ontologies like FIBO, iterate.
AI-written summary · about
chapters (8)
- 0:00Building knowledge graphs
- 10:25Graph vs knowledge graphs
- 17:28Ontologies and taxonomies
- 24:28Taxonomy standards
- 31:11Ontologies as schemas
- 35:46Building steps
- 39:00Implementation guidelines
- 40:52Q&A
related talks
44mBuilding Knowledge Graphs
46mBuilding Knowledge Graphs
21mMastering Knowledge Graph Transformations Without Compromising Meaning
24mWhy You Need a Knowledge Graph And How to Build It
30mGraph Data Science
30mEntity Resolved Knowledge Graphs
21mFrom Data to Knowledge to Action - The Graph Intelligence Platform
33mSmarter Industrial Fault Diagnosis with Knowledge Graphs and Large Language Models