Triple
T22787664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vélizy-Villacoublay |
E564013
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Viroflay |
—
|
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: Viroflay | Statement: [Vélizy-Villacoublay, borders, Viroflay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Viroflay Context triple: [Vélizy-Villacoublay, borders, Viroflay]
-
A.
Viroflay
chosen
Viroflay is a suburban commune in the Yvelines department of the Île-de-France region in north-central France, located just southwest of Paris.
-
B.
Chevroux
Chevroux is a small Swiss municipality located on the southern shore of Lake Neuchâtel in the canton of Vaud.
-
C.
Yerres
Yerres is a suburban commune in the Île-de-France region of northern France, known for its picturesque riverside landscapes that inspired Impressionist painters.
-
D.
Fins Bois
Fins Bois is a Cognac cru in the Charente region of France known for producing round, fruity eaux-de-vie that mature relatively quickly.
-
E.
Oullins
Oullins is a suburban commune in eastern France located just southwest of Lyon in the Rhône department.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c32de6481909ef358d16de98496 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:29 p.m.