A knowledge graph stores knowledge as a network of things and their relationships, for example “Berlin – is capital of – Germany”.
Illustration: AI-generated · AI Compare Ninja · CC BY 4.0
Example
A company knowledge graph links customers, contracts and contacts, so you can ask: “Who manages customer X's contracts?”
For pros
Facts are stored as triples (subject, relation, object), often in the W3C standard RDF or in graph databases. In AI systems the graph serves as a structured knowledge source alongside vector search (see GraphRAG). It is only as reliable as the data it was built from, especially if an AI created it automatically.
