Triple
T14347427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Smoleń Castle |
E355762
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Zawiercie |
—
|
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: Zawiercie | Statement: [Smoleń Castle, near, Zawiercie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zawiercie Context triple: [Smoleń Castle, near, Zawiercie]
-
A.
Zawiercie
chosen
Zawiercie is a town in southern Poland’s Silesian Voivodeship, known historically as an industrial and railway hub near the Kraków-Częstochowa Upland.
-
B.
Zgierz
Zgierz is a city in central Poland, historically part of the industrial Łódź region and notable for its textile industry and role in regional trade.
-
C.
Zwoleń
Zwoleń is a historic town in east-central Poland known for its medieval origins and association with the Renaissance poet Jan Kochanowski.
-
D.
Zawadzkie
Zawadzkie is a small town in southwestern Poland known for its industrial heritage and location within the Opole region.
-
E.
Zabrze
Zabrze is an industrial city in the Silesian region of southern Poland, historically known for coal mining and heavy industry.
- 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8e8b81bc8190ace2a575faf55cc0 |
completed | April 14, 2026, 6:59 p.m. |
Created at: April 10, 2026, 1:14 a.m.