Triple

T20283415
Position Surface form Disambiguated ID Type / Status
Subject John Lee Hancock E503209 entity
Predicate familyName P18 FINISHED
Object Hancock 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: Hancock | Statement: [John Lee Hancock, familyName, Hancock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hancock
Context triple: [John Lee Hancock, familyName, Hancock]
  • A. Hancock chosen
    Hancock is a prominent surname most famously associated with John Hancock, a key figure of the American Revolution and first signer of the United States Declaration of Independence.
  • B. Hancock
    Hancock is a small rural town in western Massachusetts known for its scenic Berkshire landscapes and outdoor recreation.
  • C. Hancock
    Hancock is a small city in Michigan’s Upper Peninsula known for its Finnish-American heritage and proximity to Lake Superior.
  • D. Hancock (film)
    Hancock is a 2008 superhero action-comedy film starring Will Smith as a troubled, alcoholic superhero seeking redemption in modern-day Los Angeles.
  • E. Kingman
    Kingman is a champion British Thoroughbred racehorse renowned for his exceptional speed and success in top-level mile races.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6769049b48190bc449557b79b9e81 completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 10:48 a.m.