Triple
T22219889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heusden-Zolder |
E549180
|
entity |
| Predicate | hasNeighbor |
P5707
|
FINISHED |
| Object | Lummen |
—
|
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: Lummen | Statement: [Heusden-Zolder, hasNeighbor, Lummen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lummen Context triple: [Heusden-Zolder, hasNeighbor, Lummen]
-
A.
Lummen
chosen
Lummen is a municipality in the Belgian province of Limburg, known for its rural character and location at the junction of several major motorways.
-
B.
Laingholm
Laingholm is a coastal residential suburb set amid native bush in the western part of Auckland, New Zealand.
-
C.
Edzell
Edzell is a small historic village in Angus, Scotland, known for its picturesque setting, nearby glens, and the ruins of Edzell Castle.
-
D.
Kildonan
Kildonan is a small coastal village on the Isle of Arran in Scotland, known for its scenic shoreline, views of the island of Pladda, and historic castle ruins.
-
E.
Kildonan
Kildonan is a rural area in Sutherland, Highland, Scotland, historically known for its 19th-century gold rush and scenic strath 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_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b8fa3d081908db0a0556b009d8f |
completed | April 28, 2026, 9:50 p.m. |
Created at: April 16, 2026, 8:37 p.m.