Triple
T23495265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chute du Doubs |
E571687
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Romandy |
—
|
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: Romandy | Statement: [Chute du Doubs, region, Romandy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Romandy Context triple: [Chute du Doubs, region, Romandy]
-
A.
Romandy
chosen
Romandy is the French-speaking western region of Switzerland, encompassing cantons such as Geneva, Vaud, Neuchâtel, and Jura.
-
B.
Neuchâtelois
Neuchâtelois refers to the inhabitants or natives of the Canton of Neuchâtel in western Switzerland, known for their French-speaking culture and heritage.
-
C.
Valentinois
Valentinois are the inhabitants or natives of Valence, a city in the Drôme department of southeastern France.
-
D.
Savognin
Savognin is a Swiss mountain village and ski resort in the canton of Graubünden, known for its alpine scenery and outdoor recreation.
-
E.
Swiss French
Swiss French is the variety of the French language spoken in the French‑speaking regions of Switzerland, characterized by distinctive vocabulary, pronunciation, and some regional usages.
- 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_69e245b4829881909b77a70e942bbd54 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7def8ac8190ade511299078d55b |
completed | April 29, 2026, 6:40 a.m. |
Created at: April 17, 2026, 6:05 p.m.