Triple
T4372339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermann Kafka |
E98924
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Julie Kafka |
E102584
|
NE FINISHED |
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: Julie Kafka | Statement: [Hermann Kafka, spouse, Julie Kafka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julie Kafka Context triple: [Hermann Kafka, spouse, Julie Kafka]
-
A.
Julie Kafka
chosen
Julie Kafka was the mother of renowned writer Franz Kafka and a member of a middle-class Jewish family in Prague.
-
B.
Ottla Kafka
Ottla Kafka was the youngest sister of writer Franz Kafka, known from his diaries and letters for their close relationship and her later persecution and death in the Holocaust.
-
C.
Valerie Kafka
Valerie Kafka was one of Franz Kafka’s sisters and a member of the Kafka family in early 20th-century Prague.
-
D.
Hermann Kafka
Hermann Kafka was a Prague businessman and the domineering father of writer Franz Kafka, whose difficult relationship with his son deeply influenced Franz's life and work.
-
E.
Gabriele Kafka
Gabriele Kafka was one of Franz Kafka’s sisters, a member of the Kafka family in early 20th-century Prague.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69b3454db3708190aeafd814413c4c3d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3521f7d9c81909c9209fe59d20ffd |
completed | March 12, 2026, 11:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5e50ec35481908cf1e1afffda19cb |
completed | March 14, 2026, 10:45 p.m. |
Created at: March 12, 2026, 11:17 p.m.