Triple

T16249420
Position Surface form Disambiguated ID Type / Status
Subject The Manxman E394459 entity
Predicate stars P1956 FINISHED
Object Anny Ondra E394457 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: Anny Ondra | Statement: [The Manxman, stars, Anny Ondra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anny Ondra
Context triple: [The Manxman, stars, Anny Ondra]
  • A. Anny Ondra chosen
    Anny Ondra was a Czech-born film actress best known as a popular leading lady in European cinema of the 1920s and 1930s and for her work with director Alfred Hitchcock.
  • B. Petra Volakova
    Petra Volakova is known as the wife of former New Jersey Devils star and Czech ice hockey player Patrik Eliáš.
  • C. Hanna Turchynova
    Hanna Turchynova is a Ukrainian academic and public figure, best known as the wife of former acting President of Ukraine Oleksandr Turchynov.
  • D. Tatiana Vilhelmová
    Tatiana Vilhelmová is a Czech film and theatre actress known for her acclaimed performances in contemporary Czech cinema and stage productions.
  • E. Hanna Novosad
    Hanna Novosad is a Ukrainian politician and public administrator who served as Minister of Education and Science in the government of Oleksiy Honcharuk.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24594f23c8190bd59fcb2585cb5e3 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0025f740ec8190ab075c953e27cfba completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:04 a.m.