Triple
T10046686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deauville |
E207632
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Knokke-Heist |
E251947
|
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: Knokke-Heist | Statement: [Deauville, twinTown, Knokke-Heist]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Knokke-Heist Context triple: [Deauville, twinTown, Knokke-Heist]
-
A.
Knokke-Heist
chosen
Knokke-Heist is a Belgian coastal resort town known for its beaches, upscale tourism, and proximity to the Dutch border.
-
B.
Tervuren
Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
-
C.
Kleine-Brogel
Kleine-Brogel is a village in the municipality of Peer in the Belgian province of Limburg, known for hosting a major military air base.
-
D.
Edegem
Edegem is a municipality in the Belgian province of Antwerp, known as a residential suburb south of the city of Antwerp.
-
E.
Schaerbeek
Schaerbeek is a multicultural municipality in the Brussels-Capital Region of Belgium, known for its Art Nouveau architecture and urban character.
- 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_69ca835ad0608190b7c80b292da004f5 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cdcf648f548190a7aa3b1594665831 |
completed | April 2, 2026, 2:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6528677f88190b259d5a25ddc290b |
completed | April 8, 2026, 1:05 p.m. |
Created at: March 30, 2026, 8:56 p.m.