Triple
T7994856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bogatynia |
E186097
|
entity |
| Predicate | borderCrossingTo |
P4105
|
FINISHED |
| Object | Hrádek nad Nisou |
E603631
|
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: Hrádek nad Nisou | Statement: [Bogatynia, borderCrossingTo, Hrádek nad Nisou]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hrádek nad Nisou Context triple: [Bogatynia, borderCrossingTo, Hrádek nad Nisou]
-
A.
Hradek nad Nisou
chosen
Hrádek nad Nisou is a small town in the Liberec Region of the Czech Republic, near the borders with Germany and Poland.
-
B.
Hrádeček
Hrádeček is a small rural settlement in the Czech Republic best known as the longtime country residence and retreat of playwright and former president Václav Havel, where he also died.
-
C.
Pohořelice
Pohořelice is a small town in the South Moravian Region of the Czech Republic, known for its agricultural surroundings and proximity to the city of Brno.
-
D.
Uherské Hradiště
Uherské Hradiště is a historic town in the Zlín Region of the Czech Republic, known as a cultural center of the Moravian Slovakia ethnographic area.
-
E.
Husinec
Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
- 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_69ca829c6c308190ab05b43d234c52b2 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c73ba388190bcedc29fbdd22f3c |
completed | March 31, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe105d400819096ba271416bb24e7 |
completed | March 31, 2026, 2:58 p.m. |
Created at: March 30, 2026, 5:17 p.m.