Triple

T17801558
Position Surface form Disambiguated ID Type / Status
Subject Hermann Kafka E444439 entity
Predicate familyOrigin P194 FINISHED
Object Osek 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: Osek | Statement: [Hermann Kafka, familyOrigin, Osek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Osek
Context triple: [Hermann Kafka, familyOrigin, Osek]
  • A. Osek chosen
    Osek is a town in the Czech Republic historically associated with the family origins of writer Franz Kafka’s father, Hermann Kafka.
  • B. Mělník
    Mělník is a historic Czech town north of Prague, known for its wine production and its location at the confluence of the Elbe and Vltava rivers.
  • C. Český Brod
    Český Brod is a historic town in the Central Bohemian Region of the Czech Republic, known for its medieval architecture and role as a former royal town on important trade routes.
  • D. Žatec
    Žatec is a historic Czech town in the Ústí nad Labem Region renowned for its long-standing hop-growing tradition and beer production.
  • E. Karviná
    Karviná is an industrial city in the Moravian-Silesian Region of the Czech Republic, historically part of Cieszyn Silesia and known for its coal mining heritage.
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e488005a288190b7a2cffa590d2557 completed April 19, 2026, 7:45 a.m.
Created at: April 10, 2026, 10:13 a.m.