Triple
T30663138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jazz Air |
E780585
|
entity |
| Predicate | mainPartnerAirline |
P36374
|
FINISHED |
| Object | Air Canada |
—
|
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: Air Canada | Statement: [Jazz Air, mainPartnerAirline, Air Canada]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainPartnerAirline Context triple: [Jazz Air, mainPartnerAirline, Air Canada]
-
A.
primaryAirlinePartner
chosen
Indicates that one airline serves as the main or preferred partner airline for another entity, such as a traveler, company, or loyalty program.
-
B.
associatedAirlineFullName
Indicates the full official name of the airline that is associated with a given entity or record.
-
C.
flightPartner
Indicates that two entities are associated as partners in operating, marketing, or coordinating a flight or set of flights.
-
D.
associatedAirlinePrimaryMarket
Indicates that an airline is primarily associated with, or operates chiefly within, a particular geographic or commercial market.
-
E.
associatedAirlineIATA
Indicates the IATA airline code that is linked or related to a given entity (such as a flight, route, or airport record).
- 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_69f70e8755a48190931eaa77946f9460 |
completed | May 3, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
Created at: April 29, 2026, 8:31 p.m.