Triple
T19559754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vieux-Nice |
E489413
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Cours Saleya |
—
|
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: Cours Saleya | Statement: [Vieux-Nice, contains, Cours Saleya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cours Saleya Context triple: [Vieux-Nice, contains, Cours Saleya]
-
A.
Cours Saleya
chosen
Cours Saleya is a famous open-air market square in Nice, France, known for its vibrant flower, food, and antique markets surrounded by cafés and historic buildings.
-
B.
Kursaal
Kursaal was the original name of the historic seaside entertainment complex and cinema now known as the Dome Cinema in Worthing, England.
-
C.
The Courser
The Courser is the English rendering of the Arabic name "Al-Adiyat," referring to the charging war-horses evoked in the 100th chapter of the Qur’an.
-
D.
Dansalan
Dansalan is the former name of Marawi, a predominantly Muslim city and the capital of Lanao del Sur in the Philippines.
-
E.
Lliçà de Vall
Lliçà de Vall is a municipality in the comarca of Vallès Oriental in the province of Barcelona, Catalonia, Spain.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63f731ae48190ade295c15db7f8ed |
completed | April 20, 2026, 3 p.m. |
Created at: April 10, 2026, 1:42 p.m.