Triple
T22789342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hallenberg |
E564064
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | Liesen |
—
|
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: Liesen | Statement: [Hallenberg, hasSubdivision, Liesen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liesen Context triple: [Hallenberg, hasSubdivision, Liesen]
-
A.
Liesen
chosen
Liesen is a small village in the Hochsauerland region of North Rhine-Westphalia, Germany, known for its rural setting and proximity to the town of Hallenberg.
-
B.
Leissigen
Leissigen is a Swiss village in the canton of Bern, known for its scenic location in the Bernese Oberland on the shores of Lake Thun.
-
C.
Líšina
Líšina is a small village in the Plzeň Region of the Czech Republic, situated within the administrative area of the Plzeň-South District.
-
D.
Liepe
Liepe is a small municipality in the district of Barnim in the German state of Brandenburg.
-
E.
Vohenstrauß
Vohenstrauß is a small town in the Upper Palatinate region of Bavaria, Germany, known for its historic architecture and surrounding forested landscapes.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c3488708190812f7d2edac92184 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:29 p.m.