Triple
T18650301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franz Kafka |
E455914
|
entity |
| Predicate | niece |
P63741
|
FINISHED |
| Object | Helena 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: Helena Davidová | Statement: [Franz Kafka, niece, Helena Davidová]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helena Davidová Context triple: [Franz Kafka, niece, Helena Davidová]
-
A.
Helena Davidová
chosen
Helena Davidová is a member of Franz Kafka’s extended family, known as the daughter of his sister Ottla Kafka.
-
B.
Helena Fibingerová
Helena Fibingerová is a former Czechoslovak shot putter who set multiple world records and won the gold medal at the 1976 Montreal Olympic Games.
-
C.
Helena Fikowa
Helena Fikowa was the wife of Polish resistance member Ignacy Fik, known primarily in historical records through her association with him.
-
D.
Zora Vesecká
Zora Vesecká is a Czech individual whose given name is Zora, a common female name in Slavic countries.
-
E.
Tatiana Vilhelmová
Tatiana Vilhelmová is a Czech film and theatre actress known for her acclaimed performances in contemporary Czech cinema and stage productions.
- 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_69d8d38ea1e88190997e9b231190ba6f |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55010d27c8190aad8d3c9e8cd31b2 |
completed | April 19, 2026, 9:58 p.m. |
Created at: April 10, 2026, 11:47 a.m.