Triple
T4430966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nièvre |
E95326
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Cosne-Cours-sur-Loire |
E167653
|
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: Cosne-Cours-sur-Loire | Statement: [Nièvre, contains, Cosne-Cours-sur-Loire]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cosne-Cours-sur-Loire Context triple: [Nièvre, contains, Cosne-Cours-sur-Loire]
-
A.
Cosne-Cours-sur-Loire
chosen
Cosne-Cours-sur-Loire is a commune in central France situated on the Loire River, known historically as a local commercial and wine-producing center.
-
B.
Roanne
Roanne is a commune and industrial town in central France, situated on the Loire River and known historically for its textile industry and river port.
-
C.
Cirque de Mourèze
Cirque de Mourèze is a striking natural amphitheater in southern France known for its dramatic dolomitic rock formations and scenic hiking trails.
-
D.
Butte-aux-Cailles
Butte-aux-Cailles is a picturesque, village-like neighborhood in Paris known for its cobbled streets, street art, and lively cafés.
-
E.
Futuroscope theme park
Futuroscope theme park is a French multimedia and technology-focused amusement park known for its immersive 3D/4D attractions, futuristic architecture, and cinematic experiences.
- 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_69b3453c2a0c8190926b574c90766db9 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3556b71448190a3fab938853f8b87 |
completed | March 13, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b627f7a8c881908a04b64d43c7b908 |
completed | March 15, 2026, 3:31 a.m. |
Created at: March 12, 2026, 11:31 p.m.