Triple

T19235523
Position Surface form Disambiguated ID Type / Status
Subject Ivan Desny E480981 entity
Predicate name P16 FINISHED
Object Ivan Desny 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: Ivan Desny | Statement: [Ivan Desny, name, Ivan Desny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ivan Desny
Context triple: [Ivan Desny, name, Ivan Desny]
  • A. Ivan Desny chosen
    Ivan Desny was a Russian-born French actor known for his prolific film and television career in European cinema from the 1950s onward.
  • B. Ivan Mayski
    Ivan Mayski was a Soviet diplomat best known for serving as the USSR’s ambassador to the United Kingdom during the Second World War.
  • C. Serge Sabarsky
    Serge Sabarsky was an Austrian-born art dealer, curator, and collector renowned for his expertise in German and Austrian Expressionist art.
  • D. Stiliyan Petrov
    Stiliyan Petrov is a retired Bulgarian footballer best known as a dynamic central midfielder for Celtic and Aston Villa, as well as a long-time captain of the Bulgarian national team.
  • E. Ivan Simanov
    Ivan Simanov is a character from the action-comedy film "Red 2," involved in the high-stakes espionage and intrigue that drive the movie’s plot.
  • 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_69d8e8ccb8f48190ad420098e74fb1db completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5faec6d0c8190b90cb1bb3160a847 completed April 20, 2026, 10:07 a.m.
Created at: April 10, 2026, 1:26 p.m.