Triple
T7487479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arras 1917 |
E176918
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Pas-de-Calais |
E63427
|
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: Pas-de-Calais | Statement: [Arras 1917, locatedIn, Pas-de-Calais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pas-de-Calais Context triple: [Arras 1917, locatedIn, Pas-de-Calais]
-
A.
Pas-de-Calais
chosen
Pas-de-Calais is a department in northern France, bordering the English Channel and known for its historic ports, World War battlefields, and the Channel Tunnel connection to the United Kingdom.
-
B.
Boulonnais
Boulonnais is a regional variety of the Picard language traditionally spoken around the Boulogne-sur-Mer area in northern France.
-
C.
Pays de Falaise
Pays de Falaise is a historical region in Normandy, France, centered around the town of Falaise and known for its medieval heritage and association with William the Conqueror.
-
D.
Seine-Maritime
Seine-Maritime is a coastal department in the Normandy region of northern France, known for its port city of Le Havre and the historic town of Rouen.
-
E.
Pays du Bessin
Pays du Bessin is a historical and coastal area in Normandy, France, encompassing several communes including parts of the D-Day landing beaches.
- 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_69c69f24ac508190bb98fe927c0bd065 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5582adc81908b68439762965d88 |
completed | March 27, 2026, 9:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84600d65481908518bc0d7ffcb373 |
completed | March 28, 2026, 9:20 p.m. |
Created at: March 27, 2026, 3:43 p.m.