Triple
T25668376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fontenay-aux-Roses station |
E643590
|
entity |
| Predicate | servedCommune |
P42362
|
FINISHED |
| Object | Fontenay-aux-Roses |
—
|
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: Fontenay-aux-Roses | Statement: [Fontenay-aux-Roses station, servedCommune, Fontenay-aux-Roses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedCommune Context triple: [Fontenay-aux-Roses station, servedCommune, Fontenay-aux-Roses]
-
A.
servesCommune
chosen
Indicates that an entity provides services or functions in support of a particular commune or local municipality.
-
B.
hasCommune
Indicates a relationship where an entity is associated with, belongs to, or is located within a specific commune (municipal administrative unit).
-
C.
isCommune
Indicates that an entity functions as or has the status of a commune, typically a local administrative or municipal unit.
-
D.
servedCommunitiesIncluding
Indicates that an entity provided services or benefits to a set of communities that includes, but may not be limited to, the specified communities.
-
E.
servedCommunitiesIn
Indicates that an entity has provided services or support to communities located within a specified area or jurisdiction.
- F. None of above.
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_69e77e7e45648190a068ed3faa8016ea |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d26ceb08819091c71c001e954936 |
completed | May 3, 2026, 4:43 a.m. |
Created at: April 21, 2026, 7:09 p.m.