Triple
T23072807
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Audience |
E575240
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Vaněk |
—
|
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: Vaněk | Statement: [Audience, hasCharacter, Vaněk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vaněk Context triple: [Audience, hasCharacter, Vaněk]
-
A.
Vaněk
chosen
Vaněk is a semi-autobiographical dissident character created by Czech playwright Václav Havel, featured in several of his politically charged plays.
-
B.
Vašek
Vašek is a common Czech diminutive form of the male given name Václav.
-
C.
Zdeněk
Zdeněk is a Czech given name commonly used for males, equivalent to the English name Sidney or Dennis in some contexts.
-
D.
Zbyněk
Zbyněk is a masculine given name of Czech origin commonly used in the Czech Republic and among Czech-speaking communities.
-
E.
Jan Veselý
Jan Veselý is a Czech professional basketball player best known as a dominant frontcourt presence in European basketball and a longtime star for Fenerbahçe in the EuroLeague.
- 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_69e245be28d48190ad1348d5a73db37d |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c60fa6c81908496f181c7d62033 |
completed | April 29, 2026, 4:43 a.m. |
Created at: April 17, 2026, 3:56 p.m.