Triple

T21994609
Position Surface form Disambiguated ID Type / Status
Subject Insidious E543172 entity
Predicate productionCompany P490 FINISHED
Object IM Global 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: IM Global | Statement: [Insidious, productionCompany, IM Global]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IM Global
Context triple: [Insidious, productionCompany, IM Global]
  • A. IM Global chosen
    IM Global is an international film and television production, financing, and sales company known for backing and distributing a wide range of independent and genre films.
  • B. United Global Services
    United Global Services is United Airlines’ invitation-only, highest-level elite status program offering exceptionally personalized service and exclusive travel benefits to its most valuable customers.
  • C. InterGlobe Enterprises
    InterGlobe Enterprises is an Indian conglomerate best known for its leadership in aviation through IndiGo airlines, along with interests in hospitality, travel, and related services.
  • D. Globalia
    Globalia is a major Spanish tourism and travel conglomerate that owns and operates various travel-related businesses, including the airline Air Europa.
  • E. JD Worldwide
    JD Worldwide is JD.com's cross-border e-commerce platform that enables Chinese consumers to purchase imported goods directly from overseas brands and merchants.
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127639bf48190800b3fa3c1527983 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:18 p.m.