Triple

T22395506
Position Surface form Disambiguated ID Type / Status
Subject Ouija E553618 entity
Predicate productionCompany P490 FINISHED
Object Hasbro Studios 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: Hasbro Studios | Statement: [Ouija, productionCompany, Hasbro Studios]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hasbro Studios
Context triple: [Ouija, productionCompany, Hasbro Studios]
  • A. Hasbro chosen
    Hasbro is a major American toy and entertainment company known for creating and owning popular brands such as Transformers, My Little Pony, and Monopoly.
  • B. Hasbro Interactive
    Hasbro Interactive was a video game publishing division of Hasbro that focused on adapting the company’s popular toy and entertainment brands into interactive titles.
  • C. Mattel Films
    Mattel Films is the film production division of the toy company Mattel, responsible for developing and producing movies based on its toy and game brands.
  • D. Kenner Products
    Kenner Products was an American toy company best known for producing popular licensed toy lines such as the original Star Wars action figures.
  • E. Mattel
    Mattel is a major American toy manufacturing company best known for creating iconic brands such as Barbie, Hot Wheels, and Fisher-Price.
  • 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_69e11e4cf87c8190a1ff474daec326b7 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1585e84b081908c95ed3e0d987ed8 completed April 29, 2026, 1:01 a.m.
Created at: April 16, 2026, 8:45 p.m.