Triple

T22505580
Position Surface form Disambiguated ID Type / Status
Subject Bolloré Group E556379 entity
Predicate brand P1500 FINISHED
Object Bluebus 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: Bluebus | Statement: [Bolloré Group, brand, Bluebus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bluebus
Context triple: [Bolloré Group, brand, Bluebus]
  • A. Bluebus chosen
    Bluebus is a French manufacturer specializing in electric buses designed for urban public transportation.
  • B. Blue Arrow
    Blue Arrow is the popular nickname of NBA guard Jamal Murray, highlighting his sharpshooting scoring style and clutch shot-making.
  • C. Buss
    Buss is a surname most notably associated with David M. Buss, an influential American evolutionary psychologist known for his work on human mating strategies.
  • D. Bix
    Bix is the nickname of Bix Beiderbecke, a pioneering American jazz cornetist and composer from the 1920s.
  • E. The Mack
    The Mack is a 1973 blaxploitation crime film centered on a charismatic pimp navigating power struggles in Oakland’s criminal underworld.
  • 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_69e11e555edc81909ca803587dafd747 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15d5bf0f0819093426d83ebd80ef0 completed April 29, 2026, 1:22 a.m.
Created at: April 16, 2026, 8:50 p.m.