Triple
T20543759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vera Čáslavská |
E504412
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Věra Čáslavská |
—
|
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: Věra Čáslavská | Statement: [Vera Čáslavská, fullName, Věra Čáslavská]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Věra Čáslavská Context triple: [Vera Čáslavská, fullName, Věra Čáslavská]
-
A.
Vera Čáslavská
chosen
Vera Čáslavská was a legendary Czech artistic gymnast and multiple Olympic gold medalist renowned for her dominance in the 1960s and her symbolic stance against the Soviet-led invasion of Czechoslovakia.
-
B.
Irena Sedlecká
Irena Sedlecká was a Czech-born British sculptor renowned for her expressive figurative works and prominent public monuments.
-
C.
Eva Němcová
Eva Němcová is a former Czech professional basketball player best known as a standout forward in the WNBA during the late 1990s and early 2000s.
-
D.
Olga Sobotková
Olga Sobotková is known as the wife of former Czech Prime Minister Bohuslav Sobotka.
-
E.
Věra Davidová
Věra Davidová was the daughter of Ottla Kafka, making her a niece of the writer Franz Kafka.
- 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a2957c308190aab81127f82f8aa6 |
completed | April 20, 2026, 10:03 p.m. |
Created at: April 16, 2026, 11:38 a.m.