Triple

T22225393
Position Surface form Disambiguated ID Type / Status
Subject The Treaty E549324 entity
Predicate hasCastMember P2308 FINISHED
Object Tom Hickey 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: Tom Hickey | Statement: [The Treaty, hasCastMember, Tom Hickey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Hickey
Context triple: [The Treaty, hasCastMember, Tom Hickey]
  • A. Tom Hickey chosen
    Tom Hickey was an Irish actor known for his extensive work in theatre, film, and television, particularly in Ireland.
  • B. Nat Hickey
    Nat Hickey was an early professional basketball player and coach best known for briefly appearing in an NBA game at age 45, making him the oldest player in league history.
  • C. Frank Horrigan
    Frank Horrigan is a veteran Secret Service agent haunted by his failure to protect President Kennedy, who becomes determined to stop a new presidential assassination plot in the thriller film "In the Line of Fire."
  • D. Frank Quinlan
    Frank Quinlan is a central character in the 1996 fantasy drama film "Michael," portrayed as one of the reporters who travels with the archangel Michael and documents his unconventional behavior.
  • E. Tom Henighan
    Tom Henighan is a researcher and co-author known for his work in large-scale language models and AI, including contributions to influential OpenAI publications.
  • 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_69e11e403d6481909a94d0aaf157f6ef completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b93e2208190aee70ffd82962ea0 completed April 28, 2026, 9:50 p.m.
Created at: April 16, 2026, 8:37 p.m.