Triple
T2295752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wallis and Futuna |
E51608
|
entity |
| Predicate | largestSettlement |
P163
|
FINISHED |
| Object | Mata-Utu |
E253671
|
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: Mata-Utu | Statement: [Wallis and Futuna, largestSettlement, Mata-Utu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mata-Utu Context triple: [Wallis and Futuna, largestSettlement, Mata-Utu]
-
A.
Mata-Utu
chosen
Mata-Utu is the main town and administrative center of the French overseas collectivity of Wallis and Futuna in the South Pacific.
-
B.
Piumafua
Piumafua is the highest peak on the island of Olosega in American Samoa, known for its steep volcanic terrain and lush tropical surroundings.
-
C.
Taulaga
Taulaga is the small principal village and only significant settlement on Swains Island in American Samoa.
-
D.
Fitiuta
Fitiuta is a small village on the island of Taʻū in American Samoa, known for its traditional Samoan culture and coastal setting.
-
E.
Nuʻuuli
Nuʻuuli is a village and commercial center on the island of Tutuila in American Samoa.
- 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_69a88b0a9f248190bcff941463d8f65a |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc5dc40f881908a3dcc518bbead55 |
completed | March 7, 2026, 6:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae960ae538819095c66b91952800b7 |
completed | March 9, 2026, 9:42 a.m. |
Created at: March 4, 2026, 7:49 p.m.