Triple

T10739608
Position Surface form Disambiguated ID Type / Status
Subject Airpoints E253285 entity
Predicate earningMethod P30192 FINISHED
Object flying with Air New Zealand 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: flying with Air New Zealand | Statement: [Airpoints, earningMethod, flying with Air New Zealand]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: earningMethod
Context triple: [Airpoints, earningMethod, flying with Air New Zealand]
  • A. trainingMethod
    Indicates the specific approach, technique, or procedure used to train an entity (such as a person, model, or system).
  • B. earnOn chosen
    Indicates that one entity gains income, profit, or returns as a result of another entity or activity.
  • C. learn
    Indicates that an entity acquires knowledge, skills, or understanding from another entity, source, or experience.
  • D. offersEducationMode
    Indicates that an entity provides a particular mode or format in which education or instruction is delivered.
  • E. usesLearningMechanism
    Indicates that one entity employs or applies a particular learning mechanism or method in its functioning or behavior.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d71043106c819091939950f532eda5 completed April 9, 2026, 2:34 a.m.
PD Predicate disambiguation batch_69d6f30df9948190ab3cdc33977fac14 completed April 9, 2026, 12:30 a.m.
Created at: April 8, 2026, 9:14 p.m.