Triple
T19826683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ermont–Valmondois line |
E476342
|
entity |
| Predicate | connectsTown |
P845
|
FINISHED |
| Object | Taverny |
—
|
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: Taverny | Statement: [Ermont–Valmondois line, connectsTown, Taverny]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taverny Context triple: [Ermont–Valmondois line, connectsTown, Taverny]
-
A.
Taverny
chosen
Taverny is a suburban commune in the northwestern outskirts of Paris, located in the Val-d'Oise department in northern France.
-
B.
Terville
Terville is a small commune in northeastern France’s Grand Est region, situated near the city of Thionville in the Moselle department.
-
C.
Vexin
Vexin is a historic region in northern France that once formed a medieval county and is now divided between the Île-de-France and Normandy areas.
-
D.
Beaumettes
Beaumettes is a small commune in southeastern France, located in the Vaucluse department within the Provence-Alpes-Côte d'Azur region.
-
E.
Tarcenay
Tarcenay is a small commune in the Doubs department of the Bourgogne-Franche-Comté region in eastern France.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656cb20788190b9deac6b8af6a55d |
completed | April 20, 2026, 4:39 p.m. |
Created at: April 10, 2026, 1:50 p.m.