Triple
T18305761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivry-sur-Seine |
E438478
|
entity |
| Predicate | hasMetroStation |
P522
|
FINISHED |
| Object | Mairie d'Ivry |
—
|
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: Mairie d'Ivry | Statement: [Ivry-sur-Seine, hasMetroStation, Mairie d'Ivry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mairie d'Ivry Context triple: [Ivry-sur-Seine, hasMetroStation, Mairie d'Ivry]
-
A.
Mairie d’Ivry
chosen
Mairie d’Ivry is a Paris Métro station in the southeastern suburb of Ivry-sur-Seine, serving as one of the endpoints of Line 7.
-
B.
Mairie d’Issy
Mairie d’Issy is a Paris Métro station in Issy-les-Moulineaux serving as a key suburban access point on the southwestern edge of the network.
-
C.
Mairie de Paris
Mairie de Paris is the municipal government and administration of the city of Paris, responsible for managing local services, urban planning, and public spaces.
-
D.
Mairie du 11e arrondissement de Paris
Mairie du 11e arrondissement de Paris is the town hall and administrative center serving Paris’s 11th arrondissement.
-
E.
Mairie du 17e arrondissement de Paris
Mairie du 17e arrondissement de Paris is the town hall and local administrative center serving Paris’s 17th arrondissement.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50183394081909b86cefaaa0a3aa8 |
completed | April 19, 2026, 4:23 p.m. |
Created at: April 10, 2026, 10:35 a.m.