Triple

T21731311
Position Surface form Disambiguated ID Type / Status
Subject Film i Väst AB E536410 entity
Predicate alsoKnownAs P39 FINISHED
Object Trollywood film fund NE NERFINISHED

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: Trollywood film fund | Statement: [Film i Väst AB, alsoKnownAs, Trollywood film fund]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trollywood film fund
Context triple: [Film i Väst AB, alsoKnownAs, Trollywood film fund]
  • A. Trollywood chosen
    Trollywood is the film industry nickname for Trollhättan, Sweden, known for its prominent movie studios and frequent use as a filming location.
  • B. Tulu cinema
    Tulu cinema is the regional film industry that produces movies in the Tulu language, primarily serving audiences in the coastal Karnataka region of India.
  • C. Nala Films
    Nala Films is an independent film production company known for financing and producing critically acclaimed feature films.
  • D. New Town Films
    New Town Films is a film production company best known for producing the Australian drama "The Sum of Us."
  • E. Tapioca Films
    Tapioca Films is a French film production company known for working on visually inventive and offbeat projects such as Jean-Pierre Jeunet’s "Micmacs à tire-larigot."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c46d3284819099a4f9d5a704eb95 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69effd0713c48190a38b3963cb3cbaf0 completed April 28, 2026, 12:19 a.m.
Created at: April 16, 2026, 6:48 p.m.