Ask DisamKB

Ask a question in plain English — an LLM agent explores DisamKB, writes a SPARQL query that answers it, and shows you both the result and the query.

Try:

Agent trace

Your question goes to an LLM agent (gpt-5.4-mini) whose only knowledge of DisamKB comes through tool calls — every step it takes streams here, live. Its loop:

  1. Search

    It finds candidate entities and properties in search indices over DisamKB's canonical labels and observed surface forms — the same disambiguation evidence the browser shows on entity pages.

  2. Verify

    It checks every E/P/C identifier with exploratory SPARQL before using it — DisamKB's ids are unknown to language models, so nothing is answered from model memory.

  3. Execute

    When a query produces the answer, it runs one final time — the result table and SPARQL rendered below are the ground truth, and you can rerun or edit the query in the editor.