Triple

T9855521
Position Surface form Disambiguated ID Type / Status
Subject Membership Rewards E239574 entity
Predicate pointsEarningBasis P32728 FINISHED
Object card purchases LITERAL FINISHED

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: card purchases | Statement: [Membership Rewards, pointsEarningBasis, card purchases]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: pointsEarningBasis
Context triple: [Membership Rewards, pointsEarningBasis, card purchases]
  • A. pointsEarnedFrom
    Indicates the number of points that an entity has received as a result of another specified source, action, or event.
  • B. mileEarningUnit chosen
    Indicates the unit or basis (e.g., per mile, per dollar) used to calculate or award mileage or points in a mileage-earning relationship.
  • C. loyaltyProgramEarnings
    Indicates the amount or details of rewards or benefits a participant accrues within a loyalty or rewards program.
  • D. earnsMorePointsThan
    Indicates that one entity receives a greater number of points than another entity in a given context or comparison.
  • E. calculationBasis
    Indicates the rule, method, or reference standard used as the foundation for performing a calculation in the relationship.
  • F. None of above.

Provenance (3 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_69ca84e6493081909cf58c8d42ea856b completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb39719288190adf45e7c029edd51 completed April 2, 2026, 12:08 a.m.
PD Predicate disambiguation batch_69cd03e73ec48190bc30fa781978d817 completed April 1, 2026, 11:39 a.m.
Created at: March 30, 2026, 8:35 p.m.