Triple
T9190993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kreol Seselwa |
E220587
|
entity |
| Predicate | spokenIn |
P2266
|
FINISHED |
| Object | La Digue |
E157235
|
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: La Digue | Statement: [Kreol Seselwa, spokenIn, La Digue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: La Digue Context triple: [Kreol Seselwa, spokenIn, La Digue]
-
A.
La Digue
chosen
La Digue is a small Seychellois island famed for its granite boulder-fringed beaches, turquoise waters, and laid-back, traditional island atmosphere.
-
B.
Porquerolles
Porquerolles is a Mediterranean island off the southern coast of France, renowned for its unspoiled beaches, pine forests, and protected natural landscapes within the Îles d'Hyères archipelago.
-
C.
Île de la Jatte
Île de la Jatte is a well-known Seine River island in the western suburbs of Paris, noted for its Impressionist art heritage and upscale residential character.
-
D.
Ile de la Motte
Île de la Motte is a small, wooded island in Lake Murten in western Switzerland, known as a local natural and recreational area.
-
E.
Île du Port
Île du Port is a remote subantarctic island that forms part of the French Kerguelen archipelago in the southern Indian Ocean.
- 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_69ca83e7ba70819088b74866d9da2c30 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd5bf25c081909e651b67ef8ecc33 |
completed | April 1, 2026, 8:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d05c272f508190aade1769c88cf16d |
completed | April 4, 2026, 12:32 a.m. |
Created at: March 30, 2026, 7:24 p.m.