Triple
T20791980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Division, Fiji |
E511799
|
entity |
| Predicate | hasMainAirport |
P17216
|
FINISHED |
| Object | Savusavu Airport |
—
|
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: Savusavu Airport | Statement: [Northern Division, Fiji, hasMainAirport, Savusavu Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Savusavu Airport Context triple: [Northern Division, Fiji, hasMainAirport, Savusavu Airport]
-
A.
Savusavu Airport
chosen
Savusavu Airport is a small domestic airport serving the town of Savusavu on the Fijian island of Vanua Levu.
-
B.
Hihifo Airport
Hihifo Airport is the main airfield serving the French overseas collectivity of Wallis and Futuna in the South Pacific, providing regional connections to Mata-Utu and surrounding islands.
-
C.
Vunisea Airport
Vunisea Airport is a small public airport serving the island of Kadavu in Fiji, providing domestic connections primarily to and from the capital, Suva.
-
D.
Tolitoli Airport
Tolitoli Airport is a regional airport serving the town and surrounding area of Tolitoli in Central Sulawesi, Indonesia.
-
E.
Talagi Airport
Talagi Airport is the main commercial airport serving the city of Arkhangelsk in northwestern Russia.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2910d488190bc4be37512effc86 |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:38 p.m.