Triple
T9349032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taha'a |
E224967
|
entity |
| Predicate | nearbyIsland |
P2064
|
FINISHED |
| Object | Bora Bora |
E212852
|
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: Bora Bora | Statement: [Taha'a, nearbyIsland, Bora Bora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bora Bora Context triple: [Taha'a, nearbyIsland, Bora Bora]
-
A.
Bora Bora
chosen
Bora Bora is a small South Pacific island renowned for its turquoise lagoon, overwater bungalows, and status as a premier luxury travel destination.
-
B.
Lefou
Lefou is the bumbling yet loyal sidekick to the villainous Gaston in Disney's live-action adaptation of "Beauty and the Beast" (2017).
-
C.
Rangiroa
Rangiroa is a vast coral atoll in French Polynesia renowned for its immense lagoon and world-class scuba diving.
-
D.
Tahiti
Tahiti is the largest island in French Polynesia, renowned for its volcanic mountains, lush rainforests, and world-famous surfing beaches in the South Pacific.
-
E.
Hiva Oa
Hiva Oa is a remote volcanic island in the Marquesas Islands of French Polynesia, known for its dramatic landscapes, archaeological sites with large tiki statues, and as the final home of artist Paul Gauguin.
- 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_69ca842993248190a79ab06968994b86 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4f1198b88190adc0b01f7c1be36e |
completed | April 1, 2026, 5 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0e43c31008190b542a9c5aa33f30e |
completed | April 4, 2026, 10:13 a.m. |
Created at: March 30, 2026, 7:41 p.m.