Triple

T7561064
Position Surface form Disambiguated ID Type / Status
Subject Taken E178794 entity
Predicate producer P490 FINISHED
Object Arnon Milchan E140363 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: Arnon Milchan | Statement: [Taken, producer, Arnon Milchan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arnon Milchan
Context triple: [Taken, producer, Arnon Milchan]
  • A. Arnon Milchan chosen
    Arnon Milchan is an Israeli film producer and businessman known for backing numerous major Hollywood films, including acclaimed hits like "L.A. Confidential."
  • B. Irwin Winkler
    Irwin Winkler is an American film producer and director best known for producing the "Rocky" series and numerous other acclaimed Hollywood films.
  • C. Ilya Salkind
    Ilya Salkind is a film producer best known for co-producing the 1970s Superman films and other major international productions.
  • D. Peter Chernin
    Peter Chernin is an American media executive and film and television producer, known for leading Fox’s entertainment operations and founding The Chernin Group.
  • E. David Katzenberg
    David Katzenberg is an American television and film producer and director known for co-creating the MTV series "The Hard Times of RJ Berger" and producing various comedy and horror projects.
  • 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_69c69f2f80288190b95cceb4da92ab2b completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f8f847c48190a1081aa9de7ff945 completed March 27, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c856d0cbfc8190b2cb2b601a7b078c completed March 28, 2026, 10:31 p.m.
Created at: March 27, 2026, 3:50 p.m.