Triple

T4977674
Position Surface form Disambiguated ID Type / Status
Subject Emma Tillinger Koskoff E111807 entity
Predicate employer P7 FINISHED
Object Sikelia Productions E113265 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: Sikelia Productions | Statement: [Emma Tillinger Koskoff, employer, Sikelia Productions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sikelia Productions
Context triple: [Emma Tillinger Koskoff, employer, Sikelia Productions]
  • A. Sikelia Productions chosen
    Sikelia Productions is the film and television production company founded by director Martin Scorsese, known for backing many of his major projects.
  • B. Cappa Productions
    Cappa Productions is a film production company best known for collaborating with director Martin Scorsese on projects such as the 1993 period drama "The Age of Innocence."
  • C. Belisarius Productions
    Belisarius Productions is a television production company founded by Donald P. Bellisario, best known for creating and producing popular series such as NCIS and JAG.
  • D. Ostar Productions
    Ostar Productions is a television production company best known for producing the crime drama series "Rizzoli & Isles."
  • E. Lyca Productions
    Lyca Productions is a prominent Indian film production and distribution company best known for financing big-budget Tamil-language movies and collaborations with leading South Indian filmmakers and stars.
  • 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_69bd441adc208190b70a033a0741d01e completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd7232bd8c8190b325c9198e8b2fa1 completed March 20, 2026, 4:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a0634b48190acb4a1834f5647cf completed March 21, 2026, 12:07 p.m.
Created at: March 20, 2026, 1:33 p.m.