Triple
T22531158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sète |
E557037
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Mont Saint-Clair |
—
|
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: Mont Saint-Clair | Statement: [Sète, hasIsland, Mont Saint-Clair]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont Saint-Clair Context triple: [Sète, hasIsland, Mont Saint-Clair]
-
A.
Mont Saint-Clair
chosen
Mont Saint-Clair is a prominent hill overlooking the Mediterranean and the town of Sète in southern France, known for its panoramic views and cultural significance.
-
B.
Mont Saint-Bruno
Mont Saint-Bruno is a small, isolated mountain in southwestern Quebec, Canada, known for its provincial park, forested trails, and proximity to Montreal.
-
C.
Mont Brome
Mont Brome is a small, isolated igneous hill in southern Quebec, Canada, known as one of the Monteregian Hills and a popular site for outdoor recreation and skiing.
-
D.
Tete Morne
Tete Morne is a small settlement located within Saint Patrick Parish on the Caribbean island nation of Dominica.
-
E.
Morne de la Grande Montagne
Morne de la Grande Montagne is the highest peak on the French archipelago of Saint Pierre and Miquelon in the North Atlantic.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed6734881908abbbee477dfab98 |
completed | April 29, 2026, 1:28 a.m. |
Created at: April 16, 2026, 8:51 p.m.