Triple

T3249157
Position Surface form Disambiguated ID Type / Status
Subject Mulan (1998 film) E68134 entity
Predicate editor P1954 FINISHED
Object Michael Kelly E296300 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: Michael Kelly | Statement: [Mulan (1998 film), editor, Michael Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Kelly
Context triple: [Mulan (1998 film), editor, Michael Kelly]
  • A. Michael Kelly
    Michael Kelly is an American actor best known for his role as Doug Stamper on the political drama series "House of Cards."
  • B. Michael Kelly chosen
    Michael Kelly is a film editor best known for his work on the animated feature "The Rescuers Down Under."
  • C. Jack Coleman
    Jack Coleman was an American professional basketball forward best known for his key role on the Rochester Royals’ 1951 NBA championship team.
  • D. Kevin Rooney
    Kevin Rooney is an American boxing trainer best known for coaching Mike Tyson during his rise to the heavyweight championship in the 1980s.
  • E. Thomas Conway
    Thomas Conway was an 18th-century Irish-born soldier who served as a general in the Continental Army during the American Revolutionary War and was a central figure in the so-called "Conway Cabal" against George Washington.
  • 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_69ad858e4c708190aa31d486cfee8a6a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaf3fc3c8819080ac95974581ca0e completed March 8, 2026, 5:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2776934108190ac405ba5ebd47084 completed March 12, 2026, 8:20 a.m.
Created at: March 8, 2026, 3:09 p.m.