Triple
T7063919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Veurne |
E164295
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Gravelines |
E403436
|
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: Gravelines | Statement: [Veurne, hasTwinTown, Gravelines]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gravelines Context triple: [Veurne, hasTwinTown, Gravelines]
-
A.
Gravelines
chosen
Gravelines is a coastal commune in northern France known for its historic fortifications and strategic position along the English Channel.
-
B.
Boulogne
Boulogne is a French football club known for being one of the early professional teams in N’Golo Kanté’s career.
-
C.
Aire-sur-la-Lys
Aire-sur-la-Lys is a historic town in northern France’s Pas-de-Calais department, known for its medieval architecture and strategic location near the Lys River.
-
D.
Boulogne-sur-Mer
Boulogne-sur-Mer is a coastal city and major fishing port in northern France, located on the English Channel in the Pas-de-Calais department.
-
E.
Calais
Calais is a major French port city on the northern coast, serving as one of the primary crossing points between France and England.
- 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_69c688796c148190adb2f1596f595f22 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e45e80e08190bb1a79a6026d2cd5 |
completed | March 27, 2026, 8:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c788ba7af88190aeaf3205255af8ad |
completed | March 28, 2026, 7:52 a.m. |
Created at: March 27, 2026, 2:38 p.m.