Triple
T1345410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gagny |
E28558
|
entity |
| Predicate | hasLocalAdministration |
P3379
|
FINISHED |
| Object | town hall of Gagny |
—
|
LITERAL 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: town hall of Gagny | Statement: [Gagny, hasLocalAdministration, town hall of Gagny]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalAdministration Context triple: [Gagny, hasLocalAdministration, town hall of Gagny]
-
A.
hasLocalGovernmentBody
chosen
Indicates that an entity is administered or overseen by a specific local government authority or governing body.
-
B.
hasAdministrativeArea
Indicates that one entity serves as the governing or jurisdictional area responsible for administering another entity.
-
C.
hasMunicipalGovernment
Indicates that an entity is administered or governed by a municipal-level governmental authority.
-
D.
hasLocalOrdinances
Indicates that a governing body or jurisdiction has established and enacted specific local ordinances or regulations.
-
E.
hasMetropolitanAuthorityOver
Indicates that one entity holds official governing or administrative authority over a metropolitan area or region associated with another entity.
- 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_69a49854eb3481908c7d56b2e449a290 |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c23d696c8190bb688274280cb680 |
completed | March 1, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69a4bef5857c81909ae984feb85a26ca |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:56 p.m.