Triple

T16827769
Position Surface form Disambiguated ID Type / Status
Subject The Howling E409064 entity
Predicate screenwriter P2831 FINISHED
Object John Sayles E536724 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: John Sayles | Statement: [The Howling, screenwriter, John Sayles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Sayles
Context triple: [The Howling, screenwriter, John Sayles]
  • A. John Sayles chosen
    John Sayles is an American independent filmmaker, screenwriter, and novelist known for his socially conscious, character-driven films.
  • B. Philip Kaufman
    Philip Kaufman is an American film director and screenwriter known for works such as "The Right Stuff," "Invasion of the Body Snatchers" (1978), and "The Unbearable Lightness of Being."
  • C. Tony Bill
    Tony Bill is an American film producer, director, and actor best known for producing the Oscar-winning film "The Sting" and directing movies such as "My Bodyguard."
  • D. Ken Hughes
    Ken Hughes was a British film director and screenwriter best known for directing the 1968 musical fantasy film "Chitty Chitty Bang Bang."
  • E. Alan Rudolph
    Alan Rudolph is an American film director and screenwriter known for his offbeat, character-driven dramas and romantic films, often blending ensemble casts with stylized, atmospheric storytelling.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b3151350819097b1c375e6df8986 completed April 18, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b2a0ac148190a7a7edebcb67c040 completed May 10, 2026, 4:30 p.m.
Created at: April 10, 2026, 5:23 a.m.