Triple
T18633540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ottla Kafka |
E455481
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Josef David |
—
|
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: Josef David | Statement: [Ottla Kafka, spouse, Josef David]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Josef David Context triple: [Ottla Kafka, spouse, Josef David]
-
A.
Josef David
chosen
Josef David was the husband of Ottla Kafka, the youngest sister of writer Franz Kafka, and a member of the Prague Jewish community in the early 20th century.
-
B.
Oskar Karlweis
Oskar Karlweis was an Austrian-born stage and film actor known for his character roles in European cinema and later in Hollywood productions.
-
C.
Josef Leimberg
Josef Leimberg is an American trumpeter, composer, and producer known for his jazz-influenced work in hip-hop and collaborations with artists like Kendrick Lamar.
-
D.
Josef Niklas
Josef Niklas was a 19th-century architect known for his work on significant religious and cultural buildings in Prague, including the Spanish Synagogue.
-
E.
Daniel Zaidenstadt
Daniel Zaidenstadt is a professional audio engineer known for his work as an assistant engineer on major hip-hop and pop recordings.
- 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.