Triple
T6340695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morbihan |
E142615
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Carnac |
E293898
|
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: Carnac | Statement: [Morbihan, contains, Carnac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carnac Context triple: [Morbihan, contains, Carnac]
-
A.
Carnac
chosen
Carnac is a commune in Brittany, northwestern France, best known for its extensive prehistoric standing stone alignments and megalithic sites.
-
B.
Tatihou
Tatihou is a small French island off the coast of Normandy known for its historic Vauban fortifications, maritime museum, and rich coastal birdlife.
-
C.
Gouvy
Gouvy is a rural municipality in the Belgian province of Luxembourg, known for its natural landscapes and proximity to the Ardennes region.
-
D.
Arlay
Arlay is a historic locality in eastern France that served as the principal seat of the noble House of Chalon-Arlay.
-
E.
Benacre
Benacre is a small coastal village and civil parish in the county of Suffolk in eastern England, known for its rural landscape and proximity to the Benacre National Nature Reserve.
- 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_69c008d5ab108190b346c465696824a9 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0674311388190bb069a07a7ff60ef |
completed | March 22, 2026, 10:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6043afb4081908d480ad868625909 |
completed | March 27, 2026, 4:14 a.m. |
Created at: March 22, 2026, 4:30 p.m.