Triple

T9135211
Position Surface form Disambiguated ID Type / Status
Subject Aeroplan E219182 entity
Predicate pointEarningSource P29971 FINISHED
Object Air Canada flights E42187 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: Air Canada flights | Statement: [Aeroplan, pointEarningSource, Air Canada flights]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Air Canada flights
Context triple: [Aeroplan, pointEarningSource, Air Canada flights]
  • A. Air Canada chosen
    Air Canada is the flag carrier and largest airline of Canada, operating extensive domestic and international passenger and cargo services.
  • B. Canadian Airlines
    Canadian Airlines was a former major Canadian carrier that operated extensive domestic and international routes before being acquired by Air Canada in 2000.
  • C. Air Canada Vacations
    Air Canada Vacations is a tour operator that offers vacation packages, including flights, hotels, and other travel services, primarily to leisure destinations served by Air Canada.
  • D. WestJet
    WestJet is a major Canadian low-cost airline known for its extensive domestic and international route network and customer-friendly service.
  • E. Air Canada Express
    Air Canada Express is a regional airline brand that operates short-haul feeder flights on behalf of Air Canada, connecting smaller communities to the mainline carrier’s network.
  • 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: pointEarningSource
Context triple: [Aeroplan, pointEarningSource, Air Canada flights]
  • A. pointsEarnedFrom
    Indicates the number of points that an entity has received as a result of another specified source, action, or event.
  • B. revenueSources
    Indicates the relationship identifying where an entity’s revenue comes from or the different streams that generate its income.
  • C. tribeReputationSource
    Indicates the origin or cause from which a tribe’s reputation is derived or influenced.
  • D. loyaltyProgramEarnings
    Indicates the amount or details of rewards or benefits a participant accrues within a loyalty or rewards program.
  • E. gainedFrom chosen
    Indicates that something is obtained, acquired, or derived as a result of a specified source or cause.
  • 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_69ca83e012288190a5771058adbaabd2 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8de0dec8190978c80b9ec8bf25c completed April 1, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05452acb481909fcf5f826caa6ae6 completed April 3, 2026, 11:59 p.m.
PD Predicate disambiguation batch_69cc6601d77881908299d58db6e64937 completed April 1, 2026, 12:25 a.m.
Created at: March 30, 2026, 7:18 p.m.