Triple
T14759304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avenue de Wagram |
E346813
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Rue de Prony |
—
|
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: Rue de Prony | Statement: [Avenue de Wagram, connectsTo, Rue de Prony]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rue de Prony Context triple: [Avenue de Wagram, connectsTo, Rue de Prony]
-
A.
Rue de Prony
chosen
Rue de Prony is a street in Paris, France, located in the 17th arrondissement and known for its elegant Haussmann-era buildings and proximity to Parc Monceau.
-
B.
Rue de Birague
Rue de Birague is a short historic street in Paris’s Marais district that forms one of the main approaches to the Place des Vosges.
-
C.
Rue de Pascale
Rue de Pascale is a street in Brussels, Belgium, located in the European Quarter near several European Union institutions.
-
D.
Rue de Mabillon
Rue de Mabillon is a small street in Paris’s 6th arrondissement, situated in the Saint-Germain-des-Prés area and known for its proximity to cafés, shops, and the Mabillon metro station.
-
E.
Rue de la Huchette
Rue de la Huchette is a narrow, historic street in Paris’s Latin Quarter known for its lively restaurants, tourist shops, and traditional Parisian atmosphere.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7f0f5a48190af008352c26574d7 |
completed | April 14, 2026, 11:04 p.m. |
Created at: April 10, 2026, 1:30 a.m.