Triple

T5741245
Position Surface form Disambiguated ID Type / Status
Subject Something Borrowed E126618 entity
Predicate producer P490 FINISHED
Object Andrew A. Kosove E395694 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: Andrew A. Kosove | Statement: [Something Borrowed, producer, Andrew A. Kosove]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew A. Kosove
Context triple: [Something Borrowed, producer, Andrew A. Kosove]
  • A. Andrew A. Kosove chosen
    Andrew A. Kosove is an American film producer and co-founder of Alcon Entertainment, known for backing major Hollywood features across genres.
  • B. Ronald M. Cohen
    Ronald M. Cohen was an American screenwriter known for his work on politically charged and socially conscious films and television projects.
  • C. Russell Gewirtz
    Russell Gewirtz is an American screenwriter best known for writing the crime thriller film "Inside Man."
  • D. Michael S. Chernuchin
    Michael S. Chernuchin is an American television writer and producer best known for his extensive work on the "Law & Order" franchise.
  • E. Andrew Weisblum
    Andrew Weisblum is an American film editor known for his work on major feature films, including collaborations with directors like Darren Aronofsky and Wes Anderson.
  • 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_69c0083179548190b384b0bf3c08ca4d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0258382908190af8787feb1e5fbcd completed March 22, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3416d3c8190a64d3f4946b84d4b completed March 23, 2026, 6:52 a.m.
Created at: March 22, 2026, 3:48 p.m.