Triple

T23468090
Position Surface form Disambiguated ID Type / Status
Subject Rocket Science E569149 entity
Predicate distributor P1951 FINISHED
Object Picturehouse 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: Picturehouse | Statement: [Rocket Science, distributor, Picturehouse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Picturehouse
Context triple: [Rocket Science, distributor, Picturehouse]
  • A. Picturehouse chosen
    Picturehouse is an American film distribution company known for releasing independent and specialty films.
  • B. Picturehouse
    Picturehouse is a UK-based chain of boutique cinemas known for screening independent, arthouse, and mainstream films in distinctive, community-focused venues.
  • C. Wellhouse
    Wellhouse is a small village in the Colne Valley area of West Yorkshire, England.
  • D. Mouse House
    Mouse House is a Bronx Zoo exhibit dedicated to showcasing a diverse collection of small rodents and other tiny mammals in naturalistic habitats.
  • E. Clock House
    Clock House is a suburban railway station in the London Borough of Bromley that provides local commuter services into central London.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6fd280c81908aae05f0851466eb completed April 29, 2026, 6:36 a.m.
Created at: April 17, 2026, 5:54 p.m.