Triple
T8341594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ʻori Tahiti |
E195928
|
entity |
| Predicate | placeOfOrigin |
P3743
|
FINISHED |
| Object | Tahiti |
E33279
|
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: Tahiti | Statement: [ʻori Tahiti, placeOfOrigin, Tahiti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tahiti Context triple: [ʻori Tahiti, placeOfOrigin, Tahiti]
-
A.
Tahiti
chosen
Tahiti is the largest island in French Polynesia, renowned for its volcanic mountains, lush rainforests, and world-famous surfing beaches in the South Pacific.
-
B.
Ouvéa Island
Ouvéa Island is a remote atoll in New Caledonia’s Loyalty Islands, noted for its white-sand beaches, turquoise lagoon, and indigenous Kanak communities.
-
C.
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.
-
D.
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.
-
E.
Lefou
Lefou is the bumbling yet loyal sidekick to the villainous Gaston in Disney's live-action adaptation of "Beauty and the Beast" (2017).
- 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_69ca82ecbdc481908a55cad8ca062d88 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7fe9efec81908e0c9ded3963bac5 |
completed | March 31, 2026, 8:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cde79e916c8190afc90c3b12c68caf |
completed | April 2, 2026, 3:50 a.m. |
Created at: March 30, 2026, 5:58 p.m.