Knowledge Graph: Four Prompts, One Schema

Choose the branch before selecting a model. Before running graph prompts, use shared/references/model-preview.md to bind the extraction and generation routes in one approved snapshot.

Structured outputs replace four separate trained systems with four prompts that share one schema: the schema is the only training data. Adapting to a new domain means changing the schema and prompt, then evaluating the result.

Say it while working:

"No NER model to train — the schema is the only training data; tightening the type Literal is our retraining step."

When a graph is the right tool

Route before you build. A knowledge graph pays off only when facts must be chained across documents, shared across agents, or checked with provenance.