Triple
T37284613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | collège de Versailles |
E925496
|
entity |
| Predicate | localisation administrative |
P153448
|
FINISHED |
| Object | Yvelines |
—
|
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: Yvelines | Statement: [collège de Versailles, localisation administrative, Yvelines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localisation administrative Context triple: [collège de Versailles, localisation administrative, Yvelines]
-
A.
cityAdministrativeRegion
chosen
Indicates that a city is located within or governed by a specific administrative region (such as a state, province, or similar jurisdiction).
-
B.
administrativeDistrictOf
Indicates that one entity serves as the administrative district or jurisdictional area governing or encompassing another entity.
-
C.
administrativeDistricts
Indicates that one entity serves as an administrative district or subdivision governed or managed by another entity.
-
D.
realmSubdivision
Indicates a hierarchical relationship where one realm is a constituent subdivision or part of a larger realm.
-
E.
municipalCountrySubdivision
Indicates that one administrative area functions as a municipal-level subdivision within the territory of a given country.
- 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_69f76eafe20c8190856d3b996a4c31a7 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbbc49da8c8190902bbb05d2477cab |
completed | May 6, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69fbb13f34b08190bbbb220ac1e6e666 |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:16 p.m.