Triple

T19697964
Position Surface form Disambiguated ID Type / Status
Subject Harvard family E473012 entity
Predicate hasNameVariant P457 FINISHED
Object Harwood NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Harwood | Statement: [Harvard family, hasNameVariant, Harwood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harwood
Context triple: [Harvard family, hasNameVariant, Harwood]
  • A. Harwood
    Harwood is a small community located near Rice Lake in Ontario, Canada, known for its lakeside setting and rural character.
  • B. Harwood chosen
    Harwood is an English-language surname borne by various notable individuals across fields such as the military, arts, and politics.
  • C. Harwood
    Harwood is a suburban residential area and community within the Metropolitan Borough of Bolton in Greater Manchester, England.
  • D. Harwood
    Harwood is a small village located in Vernon County in the U.S. state of Missouri.
  • E. Harwood
    Harwood is a small rural locality in New South Wales, Australia, situated on the Clarence River and known for its sugar industry and historic Harwood Bridge.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8e515bef88190bc30781aea50537a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e642b2baec81909ee2cd6ead632836 completed April 20, 2026, 3:13 p.m.
Created at: April 10, 2026, 1:46 p.m.