Triple
T19680388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halluin |
E472567
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Oer-Erkenschwick |
—
|
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: Oer-Erkenschwick | Statement: [Halluin, hasTwinTown, Oer-Erkenschwick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oer-Erkenschwick Context triple: [Halluin, hasTwinTown, Oer-Erkenschwick]
-
A.
Oer-Erkenschwick
chosen
Oer-Erkenschwick is a town in western Germany’s North Rhine-Westphalia region, known for its historical roots in coal mining and its location near the Ruhr industrial area.
-
B.
Herkinge
Herkinge is a small settlement located in the Dutch province of South Holland.
-
C.
Everswinkel
Everswinkel is a small municipality in western Germany known for its rural character and location in the Münsterland region of North Rhine-Westphalia.
-
D.
Onkerzele
Onkerzele is a village in the Flemish municipality of Geraardsbergen in East Flanders, Belgium.
-
E.
Ravensberg
Ravensberg was a historical county in northwestern Germany that became part of the expanding territorial holdings of Brandenburg-Prussia.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e641bf97348190bc31b00ed4ec6cad |
completed | April 20, 2026, 3:09 p.m. |
Created at: April 10, 2026, 1:45 p.m.