Triple

T22217109
Position Surface form Disambiguated ID Type / Status
Subject Vilma Bánky E549103 entity
Predicate name P16 FINISHED
Object Vilma Bánky 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: Vilma Bánky | Statement: [Vilma Bánky, name, Vilma Bánky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vilma Bánky
Context triple: [Vilma Bánky, name, Vilma Bánky]
  • A. Vilma Bánky chosen
    Vilma Bánky was a Hungarian-born silent film actress best known as a leading lady in 1920s Hollywood, particularly in romantic dramas opposite stars like Rudolph Valentino.
  • B. Emília Kováčová
    Emília Kováčová is a Slovak public figure best known as the wife of former Slovak president Michal Kováč and for her role as First Lady of Slovakia in the 1990s.
  • C. Jarmila Kratochvílová
    Jarmila Kratochvílová is a former Czechoslovak middle-distance runner best known for setting the still-standing women's 800 metres world record in 1983.
  • D. Magdaléna Husáková
    Magdaléna Husáková was the wife of former Czechoslovak president Gustáv Husák and a Slovak communist activist who was imprisoned during the Stalinist purges.
  • E. Josefina Čermáková
    Josefina Čermáková is a Czech individual known primarily in relation to her sister, Anna Čermáková.
  • 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b8c9d488190a59f571862997304 completed April 28, 2026, 9:50 p.m.
Created at: April 16, 2026, 8:37 p.m.