Triple
T16119635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bünde |
E391098
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | Bünde-Mitte |
E391098
|
NE FINISHED |
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: Bünde-Mitte | Statement: [Bünde, hasSubdivision, Bünde-Mitte]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bünde-Mitte Context triple: [Bünde, hasSubdivision, Bünde-Mitte]
-
A.
Bünde
chosen
Bünde is a small town in the German state of North Rhine-Westphalia, known historically for its cigar industry and location in the Herford district.
-
B.
Bundorf
Bundorf is a small municipality in northern Bavaria, Germany, situated in the rural Haßberge region of the Franconia area.
-
C.
Büdesheim
Büdesheim is a district (Stadtteil) of the town Bingen am Rhein in the German state of Rhineland-Palatinate.
-
D.
Büdesheim
Büdesheim is a municipality in Germany, known in part for its international town twinning, including a partnership with Saint-Cloud in France.
-
E.
Borsdorf
Borsdorf is a small municipality in the Leipzig district of Saxony, Germany, situated just east of Leipzig in a largely rural and suburban landscape.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2016d527c8190928e73661b18a914 |
completed | April 17, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff79ecea0819083aa5cb676d49f64 |
completed | May 10, 2026, 3:12 a.m. |
Created at: April 10, 2026, 5 a.m.