Triple

T22147884
Position Surface form Disambiguated ID Type / Status
Subject Leatherheads E547334 entity
Predicate screenwriter P2831 FINISHED
Object Duncan Brantley 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: Duncan Brantley | Statement: [Leatherheads, screenwriter, Duncan Brantley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duncan Brantley
Context triple: [Leatherheads, screenwriter, Duncan Brantley]
  • A. Duncan Brantley chosen
    Duncan Brantley is a screenwriter best known for co-writing the 2008 sports comedy film "Leatherheads."
  • B. Jeff Brantley
    Jeff Brantley is a former Major League Baseball relief pitcher who became a well-known baseball broadcaster and analyst.
  • C. Jamie Brinkley
    Jamie Brinkley is an individual notable enough to be recognized as a bearer of the Brinkley surname, though specific widely known public details about them are not readily available.
  • D. Drew Holt
    Drew Holt is a fictional teenage character from the television drama series "Parenthood," known for his sensitive nature and close relationship with his single mother, Amber Holt.
  • E. Kyle Bradley
    Kyle Bradley is an American mixed martial artist known for competing in the UFC’s lightweight division.
  • 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_69e11e3b52088190ad5df386d01eb2fb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129f209688190afea1f275c922c73 completed April 28, 2026, 9:43 p.m.
Created at: April 16, 2026, 8:33 p.m.