Triple

T18508428
Position Surface form Disambiguated ID Type / Status
Subject Tommy Lee Jones as Gene McClary E452262 entity
Predicate characterName P36851 FINISHED
Object Gene McClary 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: Gene McClary | Statement: [Tommy Lee Jones as Gene McClary, characterName, Gene McClary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gene McClary
Context triple: [Tommy Lee Jones as Gene McClary, characterName, Gene McClary]
  • A. Gene McClary chosen
    Gene McClary is a senior executive in the film "The Company Men" who grapples with corporate downsizing and its moral and personal consequences.
  • B. Scott Speicher
    Scott Speicher was a U.S. Navy pilot who became the first American combat casualty of the 1991 Gulf War and whose long-mysterious fate drew significant national attention.
  • C. Vincent Wettergren
    Vincent Wettergren is an actor known for his role in the acclaimed Swedish dark comedy-drama film "Force Majeure."
  • D. India Wenner
    India Wenner is a member of the Wenner family, known as a child of Rolling Stone co-founder Jann Wenner.
  • E. Johnette Howard
    Johnette Howard is an American sports journalist and author known for her insightful writing on athletes and sports culture.
  • 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_69d8d386df84819092355ebb260d848e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53344033c8190a0883aef56ba79c3 completed April 19, 2026, 7:55 p.m.
Created at: April 10, 2026, 11:36 a.m.