Triple

T21166104
Position Surface form Disambiguated ID Type / Status
Subject Marie Hácha E521566 entity
Predicate relative P37 FINISHED
Object Emil Hácha 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: Emil Hácha | Statement: [Marie Hácha, relative, Emil Hácha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emil Hácha
Context triple: [Marie Hácha, relative, Emil Hácha]
  • A. Emil Hácha chosen
    Emil Hácha was a Czech lawyer and politician who served as the last president of Czechoslovakia before and during its dismemberment under Nazi pressure.
  • B. Viktor Beneš
    Viktor Beneš is a mathematician known for his contributions to probability theory and stochastic processes.
  • C. Edvard Beneš
    Edvard Beneš was a prominent Czech statesman who served as the second President of Czechoslovakia and a key leader in the country’s resistance and diplomacy during both World Wars.
  • D. Václav
    Václav is a common Czech male given name, historically borne by several notable figures including saints, nobles, and modern politicians.
  • E. Marie Hácha
    Marie Hácha was the wife of Emil Hácha, the third President of Czechoslovakia during the late 1930s and early 1940s.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7270efe3081908a50fc601c2f958c completed April 21, 2026, 7:28 a.m.
Created at: April 16, 2026, 2:59 p.m.