Triple
T8172484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skymark Airlines |
E190855
|
entity |
| Predicate | mainCompetitor |
P6615
|
FINISHED |
| Object | Vanilla Air |
E216825
|
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: Vanilla Air | Statement: [Skymark Airlines, mainCompetitor, Vanilla Air]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vanilla Air Context triple: [Skymark Airlines, mainCompetitor, Vanilla Air]
-
A.
Vanilla Air (former)
chosen
Vanilla Air was a now-defunct Japanese low-cost airline that operated domestic and regional routes in Asia as a budget carrier under the All Nippon Airways group.
-
B.
Breeze Airways
Breeze Airways is a U.S.-based low-cost airline founded by aviation entrepreneur David Neeleman, focusing on affordable, nonstop flights between underserved city pairs.
-
C.
Island Air
Island Air was a regional airline based in Hawaii that operated inter-island flights among the major Hawaiian Islands.
-
D.
Flair Airlines
Flair Airlines is a Canadian ultra-low-cost carrier that operates domestic and select international flights, emphasizing budget-friendly travel options.
-
E.
Edelweiss Air
Edelweiss Air is a Swiss leisure airline based in Zurich that operates holiday and charter flights to vacation destinations worldwide.
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4807c9808190ad91a9c688a4c7fd |
completed | March 31, 2026, 4:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf65ed508190abb60f9189f43e5c |
completed | April 1, 2026, 6:47 a.m. |
Created at: March 30, 2026, 5:39 p.m.