Triple
T3793491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roc d’Azur |
E89712
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Fréjus |
E214446
|
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: Fréjus | Statement: [Roc d’Azur, location, Fréjus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fréjus Context triple: [Roc d’Azur, location, Fréjus]
-
A.
Fréjus
chosen
Fréjus is a historic town and seaside resort on the French Riviera in southeastern France, known for its Roman ruins and Mediterranean coastline.
-
B.
Roquebrune-Cap-Martin
Roquebrune-Cap-Martin is a picturesque coastal commune on the French Riviera in southeastern France, known for its medieval village, Mediterranean views, and proximity to Monaco.
-
C.
Saintes-Maries-de-la-Mer
Saintes-Maries-de-la-Mer is a coastal town in southern France known as a pilgrimage site and seaside resort at the edge of the Camargue wetlands.
-
D.
Antibes
Antibes is a historic resort town on the French Riviera known for its Mediterranean coastline, old town, and association with artists such as Pablo Picasso.
-
E.
Le Beausset
Le Beausset is a small commune in the Var department of southeastern France, near Toulon in the Provence-Alpes-Côte d'Azur region.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee76b809c81908312f308fbe85bf4 |
completed | March 9, 2026, 3:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5121874e8819088f79e1cf771a73a |
completed | March 14, 2026, 7:45 a.m. |
Created at: March 9, 2026, 3:15 p.m.