Triple
T22793604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westfalen |
E564180
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Herford |
—
|
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: Herford | Statement: [Westfalen, containsCity, Herford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herford Context triple: [Westfalen, containsCity, Herford]
-
A.
Herford
chosen
Herford is a historic town in northwestern Germany known for its medieval architecture and location in the region of North Rhine-Westphalia.
-
B.
Nordhorn
Nordhorn is a town in Lower Saxony, Germany, known as the administrative center of the Grafschaft Bentheim district near the Dutch border.
-
C.
Wallenhorst
Wallenhorst is a municipality in Lower Saxony, Germany, located near the city of Osnabrück.
-
D.
Delmenhorst
Delmenhorst is a mid-sized industrial and commuter city in northwestern Germany, located near Bremen in the federal state of Lower Saxony.
-
E.
Oerlinghausen
Oerlinghausen is a small town in the German state of North Rhine-Westphalia, known for its scenic Teutoburg Forest surroundings and historical roots.
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cd751f081909c7907c96c9906ea |
completed | April 29, 2026, 3:36 a.m. |
Created at: April 17, 2026, 3:30 p.m.