Triple
T17655305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuřim |
E429606
|
entity |
| Predicate | officialLanguage |
P236
|
FINISHED |
| Object | Czech |
—
|
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: Czech | Statement: [Kuřim, officialLanguage, Czech]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Czech Context triple: [Kuřim, officialLanguage, Czech]
-
A.
Czech
Czech refers to a West Slavic ethnic group native to the Czech Republic, historically associated with the region of Bohemia and the Czech language.
-
B.
Czech language
chosen
Czech language is a West Slavic language spoken primarily in the Czech Republic and known for its rich literary tradition and complex grammar.
-
C.
Czech Wikisource
Czech Wikisource is the Czech-language edition of Wikisource, a free online digital library of public domain and freely licensed texts.
-
D.
Old Czech
Old Czech is the earliest documented stage of the Czech language, used in medieval Bohemia and preserved in a variety of religious, legal, and literary texts.
-
E.
Czech American
A Czech American is a United States citizen or resident of Czech ancestry, reflecting cultural roots in the Czech Republic (formerly part of Czechoslovakia).
- 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_69d889e2c2608190b762e76d9b2262f1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46e40e344819086a49c69f8f2956b |
completed | April 19, 2026, 5:55 a.m. |
Created at: April 10, 2026, 6:06 a.m.