Triple
T17592178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Caen |
E428473
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Granville |
—
|
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: Granville | Statement: [Gare de Caen, connectsTo, Granville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Granville Context triple: [Gare de Caen, connectsTo, Granville]
-
A.
Granville
chosen
Granville is a coastal town in Normandy, France, known for its historic port, seaside resorts, and views toward the Chausey Islands.
-
B.
Granville
Granville is a locality and suburb within Queensland’s Fraser Coast Region in Australia.
-
C.
Granville
Granville is a masculine given name of English origin that has been borne by various notable individuals, including artists, politicians, and scholars.
-
D.
Granville
Granville is a town in Washington County, New York, known for its slate quarrying history and location near the Vermont border.
-
E.
Hermeville
Hermeville is a small commune in northern France located within the metropolitan area of Le Havre in the Normandy region.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469e79dac8190953a1ce8fc015b20 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 5:51 a.m.