Triple

T8630850
Position Surface form Disambiguated ID Type / Status
Subject CS100 E204396 entity
Predicate originalBrand P1501 FINISHED
Object Bombardier E97324 NE FINISHED

How this triple was built (3 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: Bombardier | Statement: [CS100, originalBrand, Bombardier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bombardier
Context triple: [CS100, originalBrand, Bombardier]
  • A. Bombardier chosen
    Bombardier is a major Canadian manufacturer of trains and rail equipment widely used by transit agencies around the world.
  • B. De Havilland Canada
    De Havilland Canada is a Canadian aircraft manufacturer best known for its rugged short takeoff and landing (STOL) regional and utility aircraft used worldwide.
  • C. Canadair
    Canadair was a Canadian aircraft manufacturer best known for producing specialized amphibious firefighting and utility aircraft before becoming part of Bombardier Aerospace.
  • D. Avro Canada
    Avro Canada was a Canadian aircraft manufacturing company best known for advanced military and experimental aircraft projects such as the CF-100 Canuck and the Avro Arrow.
  • E. de Havilland
    De Havilland is the distinguished Anglo-French family name shared by Hollywood actresses Joan Fontaine and her sister Olivia de Havilland.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: originalBrand
Context triple: [CS100, originalBrand, Bombardier]
  • A. originalMarketingName
    Indicates the original marketing or brand name under which an entity (such as a product or service) was first promoted or sold.
  • B. formerBrand chosen
    Indicates that an entity was previously used or recognized as a brand for another entity but is no longer its current brand.
  • C. parentBrand
    Indicates that one brand is the overarching or owning brand from which another brand is derived or subordinated.
  • D. hasOriginalsBrand
    Indicates that one entity is associated with, or belongs to, the Originals brand of another entity.
  • E. usedBrand
    Indicates that an entity has utilized, applied, or operated a particular brand in some context.
  • F. None of above.

Provenance (4 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_69ca834b903c8190add96cc651e1a477 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5730309081909a9a0256c9bf5f8f completed March 31, 2026, 11:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef354c5c08190bf7d3023a3473d2f completed April 2, 2026, 10:53 p.m.
PD Predicate disambiguation batch_69cc455906f8819082edd79cb4a1cf28 completed March 31, 2026, 10:06 p.m.
Created at: March 30, 2026, 6:27 p.m.