Glossary · 4 · Grounding: content, retrieval and knowledge
Knowledge graph
Also known as: GraphRAG, Enterprise knowledge graph
German: Wissensgraph
A knowledge graph is a network of entities — such as products, components, functions and documents — and the typed relationships between them, stored in a machine-readable form such as RDF, so that people and AI systems can query and reason over connected knowledge.
- Intermediate
- Expert
- Technical writers
- Technical project managers
- Developers
In one sentence
Knowledge graphs explained: connected, machine-readable knowledge about products and content, and how they make AI answers more precise.
Example
A knowledge graph records that controller C200 is part of machine M5, that topic T17 describes its reset, and that firmware 3.2 changed the procedure; the AI assistant uses these links to pick the right topic.
Explained in context
Context cards connect this term with others to answer one question. Also in British English and German.
Why it matters on your learning path
- Technical writers: Taxonomies, metadata and linked terminology — including glossaries like this one — are the building blocks of knowledge graphs.
- Technical project managers: A knowledge graph is a long-term asset that improves search, reuse and AI; it needs ownership and governance.
- Developers: Combine graph queries with vector search (“GraphRAG”) to add precise relationships to semantic similarity.
Further in this site
The information architecture and ontology glossary covers RDF, IRIs and iiRDS, the standards used to build documentation knowledge graphs. The white paper on the downloads page goes deeper.