Triple
T17921213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soest plain |
E448070
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Erwitte |
—
|
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: Erwitte | Statement: [Soest plain, contains, Erwitte]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erwitte Context triple: [Soest plain, contains, Erwitte]
-
A.
Erwitte
chosen
Erwitte is a small town in the German state of North Rhine-Westphalia, known for its historic architecture and location in the Soest district.
-
B.
Schellerten
Schellerten is a rural municipality in Lower Saxony, Germany, characterized by its agricultural landscape and small-village communities.
-
C.
Wustrow
Wustrow is a small town in the Wendland region of Lower Saxony, Germany, known for its rural character and traditional half-timbered architecture.
-
D.
Wiedensahl
Wiedensahl is a small village in Lower Saxony, Germany, best known as the birthplace of the humorist and illustrator Wilhelm Busch.
-
E.
Hagenborgh
Hagenborgh is a notable landmark building in the Dutch city of Almelo, recognized for its prominent role in the local urban 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.