Triple
T18157250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derby de la Côte d’Azur |
E434663
|
entity |
| Predicate | hasHomeStadium |
P890
|
FINISHED |
| Object | Allianz Riviera |
—
|
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: Allianz Riviera | Statement: [Derby de la Côte d’Azur, hasHomeStadium, Allianz Riviera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Allianz Riviera Context triple: [Derby de la Côte d’Azur, hasHomeStadium, Allianz Riviera]
-
A.
Allianz Riviera
chosen
Allianz Riviera is a modern multi-purpose football stadium in Nice, France, known for hosting major international tournaments and serving as the home ground of OGC Nice.
-
B.
Riviera
Riviera is a distinctive Baume & Mercier luxury sports watch collection known for its bold, angular case design and casual-elegant style.
-
C.
Riviera
Riviera is a television drama series centered on wealth, crime, and intrigue along the glamorous French Riviera.
-
D.
Riva
Riva is a surname most notably associated with Maria Riva, the actress and daughter of film legend Marlene Dietrich.
-
E.
Riva
Riva is a coastal neighborhood and popular recreational area on the Asian side of Istanbul, known for its beaches, river, and natural scenery.
- 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4debf43348190a22f23a4bbfab433 |
completed | April 19, 2026, 1:55 p.m. |
Created at: April 10, 2026, 10:30 a.m.