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.