Triple
T769066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KSFO |
E16239
|
entity |
| Predicate | focusCityFor |
P164
|
FINISHED |
| Object | Alaska Airlines |
E20454
|
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: Alaska Airlines | Statement: [KSFO, focusCityFor, Alaska Airlines]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alaska Airlines Context triple: [KSFO, focusCityFor, Alaska Airlines]
-
A.
Alaska Airlines
chosen
Alaska Airlines is a major American airline based in Seattle, known for its extensive route network along the West Coast and to Alaska, Hawaii, and beyond.
-
B.
Horizon Air
Horizon Air is a regional airline in the United States that operates short-haul flights, primarily in the Pacific Northwest, as a subsidiary of Alaska Airlines.
-
C.
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.
-
D.
Mesa Airlines
Mesa Airlines is a U.S.-based regional airline that operates feeder flights for major carriers under their brand names.
-
E.
Spirit Airlines
Spirit Airlines is an American ultra-low-cost carrier known for its no-frills service model and extensive network of domestic and Latin American routes.
- 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_69a49369a0848190af883934cee3db4c |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a70376988190be2826259f5281ab |
completed | March 1, 2026, 8:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad0e56e7fc8190a81cbd97e20fd0e6 |
completed | March 8, 2026, 5:51 a.m. |
Created at: March 1, 2026, 7:37 p.m.