Triple
T14949681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayenne |
E372757
|
entity |
| Predicate | bordersDepartment |
P224
|
FINISHED |
| Object | Ille-et-Vilaine |
E157540
|
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: Ille-et-Vilaine | Statement: [Mayenne, bordersDepartment, Ille-et-Vilaine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ille-et-Vilaine Context triple: [Mayenne, bordersDepartment, Ille-et-Vilaine]
-
A.
Ille-et-Vilaine
chosen
Ille-et-Vilaine is a department in northwestern France known for its capital Rennes and its location within the historic region of Brittany.
-
B.
Loire-Atlantique
Loire-Atlantique is a department in western France on the Atlantic coast, known for its capital Nantes and its historic and maritime heritage.
-
C.
Maine-et-Loire
Maine-et-Loire is a department in western France known for its historic towns, châteaux, and vineyards along the Loire River.
-
D.
Morbihan
Morbihan is a coastal department in the Brittany region of northwestern France, known for its historic towns, megalithic sites, and scenic Gulf of Morbihan.
-
E.
Prefecture of Manche
The Prefecture of Manche is the main administrative center and government headquarters for the Manche department in Normandy, France.
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded68fae3c81909873b113bfcaca05 |
completed | April 15, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fedd2046348190bcf8660bf3825b8f |
completed | May 9, 2026, 7:07 a.m. |
Created at: April 10, 2026, 2:39 a.m.