Triple
T14434111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mabillon station |
E357913
|
entity |
| Predicate | hasEntranceOn |
P1974
|
FINISHED |
| Object | Rue du Four |
—
|
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 du Four | Statement: [Mabillon station, hasEntranceOn, Rue du Four]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rue du Four Context triple: [Mabillon station, hasEntranceOn, Rue du Four]
-
A.
Rue du Four
chosen
Rue du Four is a historic street in Paris’s 6th arrondissement, known for its central Left Bank location near Saint-Germain-des-Prés and its mix of shops, cafés, and residential buildings.
-
B.
Rue du Fort
Rue du Fort is a street in Quebec City’s historic district, situated near the Dufferin Terrace and the iconic Château Frontenac.
-
C.
Rue de la Bûcherie
Rue de la Bûcherie is a historic street in Paris’s Latin Quarter, known for its literary heritage and proximity to landmarks like Notre-Dame Cathedral.
-
D.
Rue de la Vrillière
Rue de la Vrillière is a historic street in central Paris, known for housing the Banque de France and its proximity to major landmarks in the 1st arrondissement.
-
E.
Rue de l’Étuve
Rue de l’Étuve is a famous street in central Brussels, Belgium, best known for leading to the iconic Manneken Pis statue and its many tourist shops and waffle stands.
- 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_69d8279402a88190821ffa39ae15bccf |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91471a648190adb7b283a6a85c3e |
completed | April 14, 2026, 7:11 p.m. |
Created at: April 10, 2026, 1:18 a.m.