Triple
T20332011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tahuata |
E492506
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Vaitahu |
—
|
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: Vaitahu | Statement: [Tahuata, containsSettlement, Vaitahu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vaitahu Context triple: [Tahuata, containsSettlement, Vaitahu]
-
A.
Vaitahu
chosen
Vaitahu is the principal village and administrative center of the island of Tahuata in the Marquesas Islands of French Polynesia.
-
B.
Rarotongan
Rarotongan is a Polynesian language spoken primarily in the Cook Islands, where it serves as one of the main indigenous languages.
-
C.
Tanna
Tanna is a volcanic island in southern Vanuatu known for its active Mount Yasur volcano and traditional kastom villages.
-
D.
Tubuai
Tubuai is the main island and administrative center of the Austral Islands in French Polynesia, known for its volcanic landscape, lagoon, and role as a regional hub in the South Pacific.
-
E.
Manihiki
Manihiki is a remote coral atoll in the northern Cook Islands, known for its black pearl farming and traditional Polynesian culture.
- 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_69e0b4a1a09881908d97270d6971a25a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e677e886a08190952b828fedd2a411 |
completed | April 20, 2026, 7 p.m. |
Created at: April 16, 2026, 11:22 a.m.