Triple
T19438406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Merelbeke |
E486284
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | Merelbeke (town) |
—
|
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: Merelbeke (town) | Statement: [Merelbeke, hasSubdivision, Merelbeke (town)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Merelbeke (town) Context triple: [Merelbeke, hasSubdivision, Merelbeke (town)]
-
A.
Merelbeke
chosen
Merelbeke is a municipality in East Flanders, Belgium, known in part for hosting Ghent University's Faculty of Veterinary Medicine.
-
B.
Wielsbeke
Wielsbeke is a municipality in the Belgian province of West Flanders.
-
C.
Meerbeke
Meerbeke is a village in East Flanders, Belgium, best known for having long served as the traditional finish town of the Tour of Flanders cycling race.
-
D.
Wachtebeke
Wachtebeke is a municipality in the East Flanders province of Belgium, known for its rural character and natural areas such as the Puyenbroeck provincial domain.
-
E.
Michelbeke
Michelbeke is a village in the municipality of Brakel in East Flanders, Belgium, known for its rural character and cycling-friendly landscape.
- 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_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6336281b88190b1e5ad2606d7c314 |
completed | April 20, 2026, 2:08 p.m. |
Created at: April 10, 2026, 1:38 p.m.