Triple
T7051312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Pacific |
E163771
|
entity |
| Predicate | spokenIn |
P2266
|
FINISHED |
| Object | Rotuma |
E201780
|
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: Rotuma | Statement: [Central Pacific, spokenIn, Rotuma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rotuma Context triple: [Central Pacific, spokenIn, Rotuma]
-
A.
Rotuma
chosen
Rotuma is a remote volcanic island and dependency of Fiji in the South Pacific Ocean, known for its distinct Polynesian culture and language.
-
B.
Rurutu
Rurutu is a volcanic island in French Polynesia known for its rugged limestone cliffs, caves, and traditional Polynesian culture.
-
C.
Futuna Island
Futuna Island is a small, volcanic island in the South Pacific Ocean that forms part of the French overseas collectivity of Wallis and Futuna.
-
D.
Rarotongan
Rarotongan is a Polynesian language spoken primarily in the Cook Islands, where it serves as one of the main indigenous languages.
-
E.
Futuna-Aniwa
Futuna-Aniwa is a Polynesian language spoken primarily on the islands of Futuna and Aniwa in Vanuatu.
- 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_69c6885f598c8190b6b6495c59d8d962 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e2500570819087200013d859cfe6 |
completed | March 27, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802a126e081908ca3074b636764d1 |
completed | March 28, 2026, 4:32 p.m. |
Created at: March 27, 2026, 2:37 p.m.