Triple
T18831783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vimeu |
E460549
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Saucourt-en-Vimeu |
—
|
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: Saucourt-en-Vimeu | Statement: [Vimeu, contains, Saucourt-en-Vimeu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saucourt-en-Vimeu Context triple: [Vimeu, contains, Saucourt-en-Vimeu]
-
A.
Saucourt-en-Vimeu
chosen
Saucourt-en-Vimeu is a commune in northern France notable as the site of the 10th-century Battle of Saucourt-en-Vimeu between Frankish and Viking forces.
-
B.
Bailleul-en-Vimeu
Bailleul-en-Vimeu is a commune in northern France historically associated with the origins of the medieval Anglo-Scottish noble family, the House of Balliol.
-
C.
Courcelles-sur-Viosne
Courcelles-sur-Viosne is a small commune in the Val-d'Oise department in the Île-de-France region of northern France.
-
D.
Vroncourt-la-Côte
Vroncourt-la-Côte is a small commune in northeastern France notable as the birthplace of revolutionary anarchist and educator Louise Michel.
-
E.
Sury-en-Vaux
Sury-en-Vaux is a small rural commune in the Cher department of central France, known for its vineyards and traditional countryside setting.
- 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a99a792c81908b9a0741ef6ee782 |
completed | April 20, 2026, 4:20 a.m. |
Created at: April 10, 2026, 11:56 a.m.