Triple

T5160702
Position Surface form Disambiguated ID Type / Status
Subject Fast X E116426 entity
Predicate productionCompany P490 FINISHED
Object Original Film E197204 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: Original Film | Statement: [Fast X, productionCompany, Original Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Original Film
Context triple: [Fast X, productionCompany, Original Film]
  • A. Original Film chosen
    Original Film is an American film production company best known for producing the Fast & Furious franchise and other major Hollywood action movies.
  • B. Film Form
    Film Form is a seminal collection of essays by Soviet filmmaker Sergei Eisenstein that articulates his influential theories of montage and cinematic structure.
  • C. Film Independent
    Film Independent is a nonprofit arts organization that champions independent filmmaking and filmmakers through awards, education, and year-round programs.
  • D. Celluloid
    Celluloid is a lightweight, open-source media player for Linux that provides a simple GTK-based interface for the MPV playback engine.
  • E. Initial Film and Television
    Initial Film and Television is a British production company known for backing distinctive and often provocative film and television 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_69bd445edb3881909b93b34d260717fc completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd79073a54819080cd1e8de6fe906a completed March 20, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee07283c08190a8fc23d3041275ee completed March 21, 2026, 6:16 p.m.
Created at: March 20, 2026, 1:44 p.m.