Triple
T23230402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canal de la Deûle |
E581135
|
entity |
| Predicate | passesThrough |
P225
|
FINISHED |
| Object | Quesnoy-sur-Deûle |
—
|
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: Quesnoy-sur-Deûle | Statement: [Canal de la Deûle, passesThrough, Quesnoy-sur-Deûle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Quesnoy-sur-Deûle Context triple: [Canal de la Deûle, passesThrough, Quesnoy-sur-Deûle]
-
A.
Quesnoy-sur-Deûle
chosen
Quesnoy-sur-Deûle is a commune in northern France situated along the Deûle River within the Lille metropolitan area.
-
B.
Fricourt
Fricourt is a village in the Somme department of northern France, notable for its World War I battlefields and military cemeteries.
-
C.
Dernancourt
Dernancourt is a commune in the Somme department of northern France, known for its World War I battlefields and cemetery.
-
D.
Voujeaucourt
Voujeaucourt is a commune in eastern France’s Bourgogne-Franche-Comté region, situated near Montbéliard in the Doubs department.
-
E.
Somme-Leuze
Somme-Leuze is a rural municipality in the Walloon region of Belgium, located in the hilly Condroz area and known for its scenic countryside and small villages.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f19231ef908190a791b4967916a66f |
completed | April 29, 2026, 5:08 a.m. |
Created at: April 17, 2026, 4:09 p.m.