Triple

T11715295
Position Surface form Disambiguated ID Type / Status
Subject Nancy Allen E278479 entity
Predicate coStarredWith P14987 FINISHED
Object Tom Atkins E237859 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: Tom Atkins | Statement: [Nancy Allen, coStarredWith, Tom Atkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Atkins
Context triple: [Nancy Allen, coStarredWith, Tom Atkins]
  • A. Tom Atkins chosen
    Tom Atkins is an American character actor best known for his roles in numerous horror and thriller films, particularly in the 1980s.
  • B. John McIntire
    John McIntire was an American character actor known for his distinctive deep voice and roles in Western films and television, as well as voice work in classic Disney animated features.
  • C. Thomas Atkinson
    Thomas Atkinson is a relatively common English personal name shared by multiple notable individuals across fields such as architecture, politics, and sports.
  • D. Robert Hurst
    Robert Hurst is an American jazz bassist and composer known for his work with prominent artists and contributions to contemporary jazz recordings.
  • E. Roy Thinnes
    Roy Thinnes is an American actor best known for his leading role in the 1960s science fiction television series "The Invaders" and numerous appearances in film and television.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4bf54d88190a8e07fbbf8d9e962 completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef8397a4ac8190a71dfdd53bfa168a completed April 27, 2026, 3:41 p.m.
Created at: April 8, 2026, 9:40 p.m.