Triple

T17862592
Position Surface form Disambiguated ID Type / Status
Subject Capella International E446110 entity
Predicate hasName P744 FINISHED
Object Capella International 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: Capella International | Statement: [Capella International, hasName, Capella International]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capella International
Context triple: [Capella International, hasName, Capella International]
  • A. Capella International chosen
    Capella International is a film production company known for working on major Hollywood features, including the comedy "Austin Powers: International Man of Mystery."
  • B. Capco
    Capco is a global management and technology consultancy specializing in the financial services industry.
  • C. Polystar
    Polystar is a record label that operated as part of the international music company PolyGram, releasing a variety of popular music recordings.
  • D. Lantis
    Lantis is a Japanese music label and production company best known for producing and promoting music for anime, games, and voice actors.
  • E. Camelot Group
    Camelot Group is a British company best known for operating major lottery games, including the UK National Lottery and EuroMillions.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e49790ea148190b7a966812d44f430 completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.