Triple
T16824052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Köthen |
E408967
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Pszczyna |
—
|
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: Pszczyna | Statement: [Köthen, hasTwinTown, Pszczyna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pszczyna Context triple: [Köthen, hasTwinTown, Pszczyna]
-
A.
Pszczyna
chosen
Pszczyna is a historic town in southern Poland known for its well-preserved castle complex and picturesque old town.
-
B.
Szczekociny
Szczekociny is a small historic town in southern Poland, known for its location in the Silesian Voivodeship and the nearby site of the 1794 Battle of Szczekociny.
-
C.
Ojców
Ojców is a small village in southern Poland known as a gateway to the picturesque Ojców National Park in the Kraków-Częstochowa Upland.
-
D.
Zbrzyca
Zbrzyca is a river in northern Poland that flows through the Pomeranian region before joining the Brda River.
-
E.
Brzesko
Brzesko is a town in southern Poland known for its historical architecture and regional brewing traditions.
- 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_69d88394566c8190b3dcbdc72935f7fa |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b310ffec81908087e5aaacc4a7c2 |
completed | April 18, 2026, 4:36 p.m. |
Created at: April 10, 2026, 5:23 a.m.