Triple
T25216857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Commune of Avignon |
E631853
|
entity |
| Predicate | prefectureOf |
P128472
|
FINISHED |
| Object | Vaucluse department |
E104221
|
NE FINISHED |
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: Vaucluse department | Statement: [Commune of Avignon, prefectureOf, Vaucluse department]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prefectureOf Context triple: [Commune of Avignon, prefectureOf, Vaucluse department]
-
A.
prefectureOfHeadquarters
Indicates the administrative prefecture in which an organization's headquarters is located.
-
B.
isPrefecturalCityOf
Indicates that a city holds the administrative status of a prefecture-level city within a given region or country.
-
C.
isPrefecture
chosen
Indicates that one entity functions as an administrative prefecture governing or representing the other entity.
-
D.
hasPrefecture
Indicates that one administrative region or country possesses or is associated with a specific prefecture as a subordinate territorial unit.
-
E.
hostPrefecture
Indicates the prefecture that serves as the host location for an event, activity, or entity.
- F. None of above.
Provenance (4 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_69e75a8d1aa48190a4320acd3654762c |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f47b8f9db08190ba2d3f518fbce2c2 |
completed | May 1, 2026, 10:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1067d3f8f881909da835686315ca94 |
completed | May 22, 2026, 2:27 p.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:59 p.m.