Triple
T17551728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KMKE |
E427479
|
entity |
| Predicate | servesAirlines |
P12356
|
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: [KMKE, servesAirlines, Air Canada]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Air Canada Context triple: [KMKE, servesAirlines, Air Canada]
-
A.
Air Canada
chosen
Air Canada is the flag carrier and largest airline of Canada, operating extensive domestic and international passenger and cargo services.
-
B.
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.
-
C.
WestJet
WestJet is a major Canadian low-cost airline known for its extensive domestic and international route network and customer-friendly service.
-
D.
Canadian Airways Limited
Canadian Airways Limited was an early 20th-century Canadian airline that played a key role in pioneering commercial aviation and regional air services across Canada.
-
E.
Air Canada Express
Air Canada Express is a regional airline brand that operates short-haul feeder flights on behalf of Air Canada, connecting smaller communities to the mainline carrier’s network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e454664b348190aea3ad59954b2c91 |
completed | April 19, 2026, 4:04 a.m. |
Created at: April 10, 2026, 5:50 a.m.