Triple
T3367651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Place de Fontenoy |
E70874
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Rive Gauche |
E190187
|
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: Rive Gauche | Statement: [Place de Fontenoy, partOf, Rive Gauche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rive Gauche Context triple: [Place de Fontenoy, partOf, Rive Gauche]
-
A.
Rive gauche
chosen
Rive Gauche is the southern, traditionally bohemian and intellectual bank of the River Seine in Paris, known for its historic cafés, universities, and artistic culture.
-
B.
La Rive
La Rive is a renowned fine-dining restaurant located within Amsterdam’s historic Amstel Hotel, known for its elegant cuisine and riverside setting.
-
C.
Rive Droite
Rive Droite is the northern, historically affluent bank of the Seine in Paris, known for its grand boulevards, major museums, and iconic landmarks.
-
D.
La Rivière
La Rivière is a sector of the town of Gold, recognized as one of its notable local areas.
-
E.
Voire River
The Voire River is a small watercourse in northeastern France that flows through the Aube department, including the town of Brienne-le-Château, before joining the Aube River.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2890480819082fe2e3c2874cece |
completed | March 8, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5767842bc8190849c79a510160654 |
completed | March 14, 2026, 2:53 p.m. |
Created at: March 8, 2026, 3:13 p.m.