Triple

T19521452
Position Surface form Disambiguated ID Type / Status
Subject How She Move E488409 entity
Predicate productionCompany P490 FINISHED
Object Celluloid Dreams 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: Celluloid Dreams | Statement: [How She Move, productionCompany, Celluloid Dreams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Celluloid Dreams
Context triple: [How She Move, productionCompany, Celluloid Dreams]
  • A. Celluloid Dreams chosen
    Celluloid Dreams is an independent film production and distribution company known for championing international and art-house cinema.
  • B. Celluloid
    Celluloid is a lightweight, open-source media player for Linux that provides a simple GTK-based interface for the MPV playback engine.
  • C. Living at the Movies
    Living at the Movies is a poetry collection by American writer and punk icon Jim Carroll, known for its vivid, streetwise depictions of urban life and youth.
  • D. Hollywood Dreams
    Hollywood Dreams is an independent drama film written and directed by Henry Jaglom that explores the illusions and struggles of aspiring actors in the Hollywood film industry.
  • E. Kino-Eye
    Kino-Eye was a Soviet avant-garde film movement led by Dziga Vertov that championed documentary realism and the use of the camera as a tool to reveal truth through innovative editing and non-fiction imagery.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e635a0b37c8190b70b7427c2e85f59 completed April 20, 2026, 2:18 p.m.
Created at: April 10, 2026, 1:40 p.m.