Triple

T13083708
Position Surface form Disambiguated ID Type / Status
Subject Tootsie E310274 entity
Predicate productionCompany P490 FINISHED
Object Punch Productions E310274 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: Punch Productions | Statement: [Tootsie, productionCompany, Punch Productions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Punch Productions
Context triple: [Tootsie, productionCompany, Punch Productions]
  • A. Punch Productions chosen
    Punch Productions is a film production company best known for its involvement in the acclaimed 1982 comedy-drama "Tootsie."
  • B. Celebrated Productions
    Celebrated Productions is a film and media production company known for its work on the movie "Limelight."
  • C. Peregrine Productions
    Peregrine Productions is a film production company best known for its involvement in creating Stanley Kubrick’s 1980 horror classic "The Shining."
  • D. Corfield Productions
    Corfield Productions is a British film production company known for producing mid-20th-century films such as the adaptation of Elizabeth Taylor’s novel "A Wreath of Roses."
  • E. Primrose Hill Productions
    Primrose Hill Productions is a television production company best known for its work on the crime procedural drama series "The Mentalist."
  • 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d9811add9881908a92186dab5b6d48 completed April 10, 2026, 11 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d60e7b48819087e4583a5736c1df completed May 3, 2026, 4:58 a.m.
Created at: April 9, 2026, 9:02 p.m.