Triple

T3757628
Position Surface form Disambiguated ID Type / Status
Subject Drive, He Said E82085 entity
Predicate screenwriter P2831 FINISHED
Object Jeremy Larner E385683 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: Jeremy Larner | Statement: [Drive, He Said, screenwriter, Jeremy Larner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeremy Larner
Context triple: [Drive, He Said, screenwriter, Jeremy Larner]
  • A. Jeremy Larner chosen
    Jeremy Larner is an American writer and political speechwriter best known for winning an Academy Award for his screenplay for the film "The Candidate."
  • B. David Cromer
    David Cromer is an American director and actor known for his acclaimed work in theater, including innovative stage productions and performances on and off Broadway.
  • C. Stephen Schiff
    Stephen Schiff is an American screenwriter and journalist known for his work on films such as "Wall Street: Money Never Sleeps" and for writing on acclaimed television series.
  • D. James S. Levine
    James S. Levine is an American television composer known for scoring numerous popular TV series, including crime and drama shows.
  • E. Robert Mann
    Robert Mann was a 19th-century American man best known as the son of influential education reformer Horace Mann.
  • 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_69ad8b1db40081908b61ffa6b78afd4d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcbc04d348190b0e4a90d18bdd160 completed March 8, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f0321c4c8190ba372148c483c4ca completed March 14, 2026, 5:20 a.m.
Created at: March 8, 2026, 3:35 p.m.