Triple
T622565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toronto Pearson International Airport |
E14544
|
entity |
| Predicate | focusCityFor |
P164
|
FINISHED |
| Object | WestJet |
E63601
|
NE 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: WestJet | Statement: [Toronto Pearson International Airport, focusCityFor, WestJet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WestJet Context triple: [Toronto Pearson International Airport, focusCityFor, WestJet]
-
A.
WestJet
chosen
WestJet is a major Canadian low-cost airline known for its extensive domestic and international route network and customer-friendly service.
-
B.
Air Canada
Air Canada is the flag carrier and largest airline of Canada, operating extensive domestic and international passenger and cargo services.
-
C.
Canadian Airlines
Canadian Airlines was a former major Canadian carrier that operated extensive domestic and international routes before being acquired by Air Canada in 2000.
-
D.
Continental Airlines
Continental Airlines was a major American airline that operated extensive domestic and international routes before merging with United Airlines to form one of the world’s largest carriers.
-
E.
Frontier Airlines
Frontier Airlines is a U.S. ultra-low-cost carrier known for its point-to-point route network, animal-themed aircraft tails, and extensive domestic service.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e402d9c8190936896e3ebb6edc5 |
completed | March 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a66662e848819095aca23ceb5eeef2 |
completed | March 3, 2026, 4:41 a.m. |
Created at: March 1, 2026, 7:35 p.m.