Triple
T22307334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petit-Rhône |
E551413
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Saintes-Maries-de-la-Mer |
—
|
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: Saintes-Maries-de-la-Mer | Statement: [Petit-Rhône, nearbySettlement, Saintes-Maries-de-la-Mer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saintes-Maries-de-la-Mer Context triple: [Petit-Rhône, nearbySettlement, Saintes-Maries-de-la-Mer]
-
A.
Saintes-Maries-de-la-Mer
chosen
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.
-
B.
Dives-sur-Mer
Dives-sur-Mer is a coastal commune in northwestern France, known for its historic harbor linked to William the Conqueror’s 1066 expedition to England.
-
C.
Hyères
Hyères is a coastal town in southeastern France known for its Mediterranean climate, historic old town, and nearby Golden Islands (Îles d’Hyères).
-
D.
Luc-sur-Mer
Luc-sur-Mer is a coastal commune in northwestern France, situated on the English Channel in the Normandy region.
-
E.
La Seyne-sur-Mer
La Seyne-sur-Mer is a coastal town in southeastern France on the Mediterranean, historically known for its major shipbuilding industry.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1574bccb08190a6236dd14cf0fc5b |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.