Triple
T6232647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Pelée |
E139392
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Saint-Pierre |
E578453
|
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: Saint-Pierre | Statement: [Mount Pelée, near, Saint-Pierre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Pierre Context triple: [Mount Pelée, near, Saint-Pierre]
-
A.
Saint-Pierre
Saint-Pierre is the main town and administrative center of the French overseas collectivity of Saint Pierre and Miquelon, located off the coast of Newfoundland in the North Atlantic.
-
B.
Saint-Pierre
chosen
Saint-Pierre is a town on the Caribbean island of Martinique that was once its cultural and economic capital before being famously devastated by the 1902 eruption of Mount Pelée.
-
C.
Port-aux-Français
Port-aux-Français is the main French scientific research station and administrative center on the remote Kerguelen Islands in the southern Indian Ocean.
-
D.
Sainte-Marie
Sainte-Marie is a French designation for Saint Mary, the mother of Jesus, commonly used as a namesake for religious institutions and places.
-
E.
Grande-Île
Grande-Île is the principal and largest island of the Chausey archipelago off the coast of Normandy, France.
- 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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062ee6f088190bf72692eb8ffb761 |
completed | March 22, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c243f785dc819084d2a11151d84227 |
completed | March 24, 2026, 7:57 a.m. |
Created at: March 22, 2026, 4:22 p.m.