Triple
T23222835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quebec Route 138 |
E580937
|
entity |
| Predicate | crossesMunicipality |
P13729
|
FINISHED |
| Object | Beaupré |
—
|
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: Beaupré | Statement: [Quebec Route 138, crossesMunicipality, Beaupré]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beaupré Context triple: [Quebec Route 138, crossesMunicipality, Beaupré]
-
A.
Beaupré
chosen
Beaupré is a small riverside town in Quebec, Canada, best known as the gateway to the Mont-Sainte-Anne ski resort and the nearby Sainte-Anne-de-Beaupré Basilica.
-
B.
Vallières
Vallières is a commune in the Nord-Est department of Haiti, known as a small rural settlement within the country’s northern region.
-
C.
Butte-aux-Cailles
Butte-aux-Cailles is a picturesque, village-like neighborhood in Paris known for its cobbled streets, street art, and lively cafés.
-
D.
Roche-d’Or
Roche-d’Or is a former Swiss municipality in the canton of Jura that was incorporated into the larger municipality of Haute-Ajoie.
-
E.
Marquenterre
Marquenterre is a coastal natural area in northern France renowned for its dunes, wetlands, and rich birdlife, particularly within the Baie de Somme.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922a452c81909b48df157643f6bd |
completed | April 29, 2026, 5:07 a.m. |
Created at: April 17, 2026, 4:08 p.m.