Triple
T20576039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zdeněk Neubauer |
E505219
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Zdeněk |
—
|
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: Zdeněk | Statement: [Zdeněk Neubauer, givenName, Zdeněk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zdeněk Context triple: [Zdeněk Neubauer, givenName, Zdeněk]
-
A.
Zdeněk
chosen
Zdeněk is a Czech given name commonly used for males, equivalent to the English name Sidney or Dennis in some contexts.
-
B.
Jiří
Jiří is a common Czech male given name, equivalent to George in English.
-
C.
Zdeněk Nehoda
Zdeněk Nehoda is a former Czech footballer, widely regarded as one of Czechoslovakia’s leading forwards of the 1970s and early 1980s.
-
D.
Josef Zítek
Josef Zítek was a 19th-century Czech architect best known for his monumental Neo-Renaissance designs that helped shape Prague’s cultural and urban landscape.
-
E.
Augustin Žídek
Augustin Žídek is a researcher in computational biology and machine learning, known for co-authoring the landmark 2021 Nature paper on AlphaFold’s protein structure prediction.
- 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_69e0b4b721588190993ac7b0a9be2736 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a90af3608190955d2c7950726178 |
completed | April 20, 2026, 10:30 p.m. |
Created at: April 16, 2026, 11:39 a.m.