Definition · data infrastructure
Knowledge graph
Knowledge graph is a graph-based representation of real-world entities and the relationships between them, used to connect data across sources and support querying and reasoning. For knowledge graph, the useful boundary is the data, tools, approvals, human review, evaluation standard, and decision the system may influence.
Also known as enterprise knowledge graph, semantic graph
Why it matters
Understanding knowledge graph matters because AI-assisted finance work can sound confident even when data, assumptions, or compute paths are wrong. A useful definition keeps the output grounded, reviewable, and accountable. Pluvo models finance as a connected, bitemporal knowledge graph of entities and claims rather than indexing documents for vector search, so every answer is computed over governed structure and traces back to source.
In practice
Governance example
Teams use knowledge graph when they evaluate whether an AI-assisted analysis can be trusted. The useful test is whether the output is tied to approved data, repeatable logic, human review, and an audit trail.
Pluvo example
Pluvo models finance as a connected, bitemporal knowledge graph of entities and claims rather than indexing documents for vector search, so every answer is computed over governed structure and traces back to source.
In practice, teams should define knowledge graph with a clear source, owner, time period, and decision before they use it in reporting, planning, or operating reviews.
Understanding knowledge graph matters because AI-assisted finance work can sound confident even when data, assumptions, or compute paths are wrong. A useful definition keeps the output grounded, reviewable, and accountable. Pluvo models finance as a connected, bitemporal knowledge graph of entities and claims rather than indexing documents for vector search, so every answer is computed over governed structure and traces back to source.
A strong workflow for knowledge graph separates the definition from the action: first agree what the term means, then decide how it is measured, when it changes, and who is accountable for the next step.
Pluvo models finance as a connected, bitemporal knowledge graph of entities and claims rather than indexing documents for vector search, so every answer is computed over governed structure and traces back to source.
FAQ
What is a knowledge graph?
Knowledge graph is a graph-based representation of real-world entities and the relationships between them, used to connect data across sources and support querying and reasoning. For knowledge graph, the useful boundary is the data, tools, approvals, human review, evaluation standard, and decision the system may influence.
How is a knowledge graph different from a database?
The boundary for knowledge graph differs from related terms by scope, source data, time period, and decision use. In this glossary, it covers a graph-based representation of real-world entities and the relationships between them, used to connect data across sources and support querying and reasoning, so teams should compare those boundaries before using it in reporting or planning.
Why use a knowledge graph instead of RAG?
To use knowledge graph, start with the decision, then confirm the source data, timing, calculation logic, and owner. The analysis is strongest when a reviewer can trace the answer back to the records that produced it.