Triple

T9801997
Position Surface form Disambiguated ID Type / Status
Subject Tom Atkins E237859 entity
Predicate workedWith P398 FINISHED
Object Fred Dekker E710710 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: Fred Dekker | Statement: [Tom Atkins, workedWith, Fred Dekker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fred Dekker
Context triple: [Tom Atkins, workedWith, Fred Dekker]
  • A. Fred Dekker chosen
    Fred Dekker is an American filmmaker and screenwriter best known for cult horror and sci-fi films such as "Night of the Creeps," "The Monster Squad," and his collaborations with Shane Black.
  • B. David Friedkin
    David Friedkin was an American screenwriter, director, and producer known for his work in mid-20th-century film and television.
  • C. John Carpenter
    John Carpenter is an American filmmaker and composer best known for directing influential horror and science fiction films such as "Halloween," "The Thing," and "Escape from New York."
  • D. John McTiernan
    John McTiernan is an American film director best known for influential action movies such as "Die Hard" and "Predator."
  • E. Brad Anderson
    Brad Anderson is an American film and television director known for psychological thrillers and genre films such as "The Machinist" and "Session 9."
  • 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_69ca84dd4608819097ff4ed00feca280 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda62b41048190bcef70a7591830c6 completed April 1, 2026, 11:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc53c3dc819084a4d8b72164a172 completed April 5, 2026, 2:43 a.m.
Created at: March 30, 2026, 8:29 p.m.