Triple
T20791962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Division, Fiji |
E511799
|
entity |
| Predicate | containsIsland |
P970
|
FINISHED |
| Object | Wakaya |
E1147363
|
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: Wakaya | Statement: [Northern Division, Fiji, containsIsland, Wakaya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wakaya Context triple: [Northern Division, Fiji, containsIsland, Wakaya]
-
A.
Wakaya
chosen
Wakaya is a privately owned island in Fiji renowned for its exclusive luxury resort, pristine beaches, and surrounding coral reefs.
-
B.
Wakata
Wakata is a Japanese surname most notably associated with astronaut Koichi Wakata, a veteran Japan Aerospace Exploration Agency (JAXA) spacefarer.
-
C.
Nakawa
Nakawa is one of the energetic human hosts in Disney’s “Festival of the Lion King” stage show at Disney’s Animal Kingdom.
-
D.
Tatewari
Tatewari is a central fire deity in Wixárika (Huichol) religion, associated with ancestral wisdom, ritual purification, and the sacred use of peyote.
-
E.
Kawki
Kawki is an indigenous Andean language closely related to Aymara and spoken by a small number of people in Peru.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2910d488190bc4be37512effc86 |
completed | April 21, 2026, 12:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a090069bee8819086d6735f4f8b94c0 |
completed | May 16, 2026, 11:40 p.m. |
Created at: April 16, 2026, 12:38 p.m.