Triple
T8939170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bora Bora |
E212852
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object | Tahaa |
E224967
|
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: Tahaa | Statement: [Bora Bora, hasNearbyIsland, Tahaa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tahaa Context triple: [Bora Bora, hasNearbyIsland, Tahaa]
-
A.
Bora Bora
Bora Bora is a small South Pacific island renowned for its turquoise lagoon, overwater bungalows, and status as a premier luxury travel destination.
-
B.
Rangiroa
Rangiroa is a vast coral atoll in French Polynesia renowned for its immense lagoon and world-class scuba diving.
-
C.
Lefou
Lefou is the bumbling yet loyal sidekick to the villainous Gaston in Disney's live-action adaptation of "Beauty and the Beast" (2017).
-
D.
Tahiti Nui
Tahiti Nui is the larger, northwestern part of the island of Tahiti in French Polynesia, known for its volcanic mountains, lush landscapes, and role as the main population and economic center of the territory.
-
E.
Taha'a
chosen
Taha'a is a small island in the Society Islands of French Polynesia, renowned for its vanilla plantations, tranquil lagoons, and traditional Polynesian culture.
- 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66b7484481909e0d7610552f5386 |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1eb308c81909f5be133c75ad568 |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:58 p.m.