Triple
T5370057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Nantes |
E108824
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | La Roche-sur-Yon |
E235002
|
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: La Roche-sur-Yon | Statement: [Gare de Nantes, connectsTo, La Roche-sur-Yon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: La Roche-sur-Yon Context triple: [Gare de Nantes, connectsTo, La Roche-sur-Yon]
-
A.
La Roche-sur-Yon
chosen
La Roche-sur-Yon is a planned administrative and commercial center in western France that serves as the prefecture of the Vendée department.
-
B.
Chapeauroux
Chapeauroux is a river in central France that flows through the Massif Central before joining the Allier.
-
C.
Angers
Angers is a historic city in western France known for its medieval architecture, including the Château d'Angers and its famous Apocalypse Tapestry.
-
D.
Niort
Niort is a historic city in western France known as an administrative and economic center, particularly for its strong mutual insurance and financial services sector.
-
E.
Bourgueil
Bourgueil is a Loire Valley wine appellation in France renowned for its red wines, particularly those made predominantly from Cabernet Franc.
- 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_69bd440c77948190aad2a5f39b7b80f5 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd86873e0c8190bf5ecede2cc2bd8b |
completed | March 20, 2026, 5:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfabe6de448190a4e0c2e537a2e045 |
completed | March 22, 2026, 8:44 a.m. |
Created at: March 20, 2026, 2:02 p.m.