Triple

T4625960
Position Surface form Disambiguated ID Type / Status
Subject Donnie Brasco E101097 entity
Predicate producer P490 FINISHED
Object Barry Levinson E73903 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: Barry Levinson | Statement: [Donnie Brasco, producer, Barry Levinson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barry Levinson
Context triple: [Donnie Brasco, producer, Barry Levinson]
  • A. Barry Levinson chosen
    Barry Levinson is an American filmmaker and screenwriter best known for directing acclaimed films such as "Rain Man," "Diner," and "Good Morning, Vietnam."
  • B. David Dobkin
    David Dobkin is an American film director and producer best known for his work on hit comedies such as "Wedding Crashers."
  • C. Woody Platt
    Woody Platt is an American bluegrass musician best known as a founding member, guitarist, and lead vocalist of the Grammy-winning band Steep Canyon Rangers.
  • D. Zack Mazursky
    Zack Mazursky is a fictional teenager in the crime drama film "Alpha Dog," whose kidnapping and murder are central to the movie’s plot, inspired by the real-life Nicholas Markowitz case.
  • E. Sydney Pollack
    Sydney Pollack was an American film director, producer, and actor known for acclaimed movies such as "Out of Africa," "Tootsie," and "The Firm."
  • 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_69bd43d0497c8190ac23c65c5804846a completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a08ef488190af46418229309b0f completed March 20, 2026, 2:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69be0360f7548190b4d1c2e0e53985e8 completed March 21, 2026, 2:33 a.m.
Created at: March 20, 2026, 1:13 p.m.