Triple
T30663151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jazz Air |
E780585
|
entity |
| Predicate | frequentFlyerProgramViaPartner |
P71955
|
FINISHED |
| Object | Aeroplan |
—
|
NE NERFINISHED |
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: Aeroplan | Statement: [Jazz Air, frequentFlyerProgramViaPartner, Aeroplan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frequentFlyerProgramViaPartner Context triple: [Jazz Air, frequentFlyerProgramViaPartner, Aeroplan]
-
A.
associatedWithFrequentFlyerProgram
Indicates that an entity has a connection or involvement with a frequent flyer program, such as membership, participation, or affiliation.
-
B.
frequentPartner
Indicates that two entities regularly engage in a shared activity or interaction together more often than with others.
-
C.
loyaltyProgramPartner
chosen
Indicates that there is a partnership or affiliation between entities within the same loyalty or rewards program.
-
D.
primaryAirlinePartner
Indicates that one airline serves as the main or preferred partner airline for another entity, such as a traveler, company, or loyalty program.
-
E.
partnerInFlight
Indicates that two or more entities are collaborating or jointly participating in the same flight or air travel activity.
- 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_69f224a6d10481909290be1a00fc83b3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f697eabb048190bc01a830f14942c6 |
completed | May 3, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69f69664142c8190bc695501056b0236 |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 29, 2026, 8:31 p.m.