Triple

T13119179
Position Surface form Disambiguated ID Type / Status
Subject Thoroughbreds E311678 entity
Predicate screenwriter P2831 FINISHED
Object Cory Finley E1033318 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: Cory Finley | Statement: [Thoroughbreds, screenwriter, Cory Finley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cory Finley
Context triple: [Thoroughbreds, screenwriter, Cory Finley]
  • A. Cory Finley chosen
    Cory Finley is an American filmmaker and playwright best known for his darkly comedic and psychologically driven films such as "Thoroughbreds" and "Bad Education."
  • B. Corey McCormick
    Corey McCormick is an American bassist best known for his work with Neil Young and the rock band Lukas Nelson & Promise of the Real.
  • C. Michael Farris
    Michael Farris is an American lawyer and conservative activist best known for his leadership in the Christian homeschooling movement and his role in founding and guiding Patrick Henry College.
  • D. Ron Feemster
    Ron Feemster is a music producer known for his work on the album "Afrodisiac."
  • E. Michael Harris
    Michael Harris is a quirky, fast-talking yuppie character from the TV sitcom "Newhart," known for his neurotic personality and comedic relationship with Stephanie Vanderkellen.
  • 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_69d806a9fe888190b081e2d9ea665d6c completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98196e69081909111407ee3d9f08e completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f71f0ff20081909f277d9c8dc8b043 completed May 3, 2026, 10:10 a.m.
Created at: April 9, 2026, 9:06 p.m.