Triple

T1846255
Position Surface form Disambiguated ID Type / Status
Subject John Butler E41289 entity
Predicate name P16 FINISHED
Object John Butler E41289 NE FINISHED

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: John Butler | Statement: [John Butler, name, John Butler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Butler
Context triple: [John Butler, name, John Butler]
  • A. John Butler chosen
    John Butler was a prominent Loyalist military leader during the American Revolutionary War, best known for commanding Butler's Rangers in frontier campaigns against American revolutionaries.
  • B. Marlon Williams
    Marlon Williams is a New Zealand singer-songwriter and guitarist known for his distinctive tenor voice and genre-blending blend of folk, country, and indie rock.
  • C. Michael Coulter
    Michael Coulter is a British cinematographer known for his work on popular films including the romantic comedy "Love Actually."
  • D. Ben Harper
    Ben Harper is an American singer-songwriter and multi-instrumentalist known for blending folk, blues, rock, and reggae influences in his music.
  • E. Richard Butler
    Richard Butler was an American Revolutionary War officer and frontiersman whose military service on the early western frontier led to several U.S. counties being named in his honor.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88648cd44819093303206d96d76ad completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb051640c819088a8b28a03f57331 completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1c6941081909cef987ebe4b4d6c completed March 8, 2026, 7:45 p.m.
Created at: March 4, 2026, 7:33 p.m.