Triple
T11628895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palais de l’Institut de France |
E276344
|
entity |
| Predicate | hasMainEntranceOn |
P1974
|
FINISHED |
| Object | quai de Conti |
E263403
|
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: quai de Conti | Statement: [Palais de l’Institut de France, hasMainEntranceOn, quai de Conti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: quai de Conti Context triple: [Palais de l’Institut de France, hasMainEntranceOn, quai de Conti]
-
A.
Quai de Conti
chosen
Quai de Conti is a historic riverside quay on the Left Bank of the Seine in central Paris, known for its cultural institutions and picturesque views.
-
B.
Quai de la Douane
Quai de la Douane is a waterfront quay in the Port of Nice, France, serving as a docking and loading area for maritime traffic.
-
C.
Quai de l’Archevêché
Quai de l’Archevêché is a riverside quay on Paris’s Île de la Cité, known for its views of Notre-Dame Cathedral and its location along the Seine.
-
D.
Quai de Bourbon
Quai de Bourbon is a historic riverside quay on the Île Saint-Louis in central Paris, known for its elegant 17th-century townhouses and views over the Seine.
-
E.
Quai de la Corse
Quai de la Corse is a riverside quay on Paris’s Île de la Cité, lining the Seine near landmarks such as the flower market and Notre-Dame Cathedral.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aafa51148190ab84940694c00235 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a127b2688190ae3a340f851e834b |
completed | April 10, 2026, 7:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f43f59c6108190a9c4c7b17c2fb401 |
completed | May 1, 2026, 5:51 a.m. |
Created at: April 8, 2026, 9:39 p.m.