Triple
T18633557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franz Kafka |
E455482
|
entity |
| Predicate | auntOrUncle |
P3525
|
FINISHED |
| Object | Věra Davidová |
—
|
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 Davidová | Statement: [Franz Kafka, auntOrUncle, Věra Davidová]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Věra Davidová Context triple: [Franz Kafka, auntOrUncle, Věra Davidová]
-
A.
Věra Davidová
chosen
Věra Davidová was the daughter of Ottla Kafka, making her a niece of the writer Franz Kafka.
-
B.
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.
-
C.
Dana Vávrová
Dana Vávrová was a Czech-born German actress and film director known for her acclaimed performances in European cinema and collaborations with director Joseph Vilsmaier.
-
D.
Madla Vaculíková
Madla Vaculíková is best known as the wife of prominent Czech writer and dissident Ludvík Vaculík.
-
E.
Věra Hrabánková
Věra Hrabánková is the wife of Czech-born writer Milan Kundera and has long been known as his close partner and literary collaborator.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54fc74d208190bfda63b5b0b160cd |
completed | April 19, 2026, 9:57 p.m. |
Created at: April 10, 2026, 11:46 a.m.