Triple
T19459513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nuku Hiva Airport |
E486829
|
entity |
| Predicate | primaryAirlineService |
P12356
|
FINISHED |
| Object | Air Tahiti |
—
|
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 Tahiti | Statement: [Nuku Hiva Airport, primaryAirlineService, Air Tahiti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Air Tahiti Context triple: [Nuku Hiva Airport, primaryAirlineService, Air Tahiti]
-
A.
Air Tahiti
chosen
Air Tahiti is a regional airline based in French Polynesia that operates domestic and inter-island flights across the territory’s archipelagos.
-
B.
Air Tahiti Nui
Air Tahiti Nui is a French Polynesian airline that operates long-haul international flights, primarily connecting Tahiti with major destinations such as Los Angeles, Paris, and Auckland.
-
C.
Air Pacific
Air Pacific was the former name of Fiji’s national airline, now known as Fiji Airways.
-
D.
Samoa Airways
Samoa Airways is the national airline of Samoa, operating regional passenger services across the South Pacific.
-
E.
Air Austral
Air Austral is a French airline based in Réunion that operates regional and long-haul flights primarily within the Indian Ocean region and to Europe.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633c6c55c8190965ada884f17c800 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:38 p.m.