Triple
T15320743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiva Oa |
E366282
|
entity |
| Predicate | hasAirport |
P105
|
FINISHED |
| Object | Hiva Oa Airport |
E353996
|
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: Hiva Oa Airport | Statement: [Hiva Oa, hasAirport, Hiva Oa Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hiva Oa Airport Context triple: [Hiva Oa, hasAirport, Hiva Oa Airport]
-
A.
Hiva Oa Airport
chosen
Hiva Oa Airport is a small regional airport in the Marquesas Islands of French Polynesia that serves the island of Hiva Oa and its main village, Atuona.
-
B.
Nuku Hiva Airport
Nuku Hiva Airport is the main air gateway serving the island of Nuku Hiva in French Polynesia’s remote Marquesas Islands archipelago.
-
C.
Tafuna Airport
Tafuna Airport is the main international airport serving American Samoa, located near Pago Pago on the island of Tutuila.
-
D.
Kekaha Airport
Kekaha Airport is a small public airport on the island of Kauai in Hawaii, serving the local community with general aviation facilities.
-
E.
Nikunau Airport
Nikunau Airport is a small public airstrip serving the remote island of Nikunau in the Republic of Kiribati, providing vital regional air connectivity.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd460288190b5c41f0a0aeee949 |
completed | April 16, 2026, 1:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fef8a9085881909904152c32b0fed1 |
completed | May 9, 2026, 9:04 a.m. |
Created at: April 10, 2026, 3:16 a.m.