Triple

T13750015
Position Surface form Disambiguated ID Type / Status
Subject Roberto Benigni E330321 entity
Predicate portrayed P1668 FINISHED
Object Giorgio Perlasca E206521 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: Giorgio Perlasca | Statement: [Roberto Benigni, portrayed, Giorgio Perlasca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Giorgio Perlasca
Context triple: [Roberto Benigni, portrayed, Giorgio Perlasca]
  • A. Giorgio Perlasca chosen
    Giorgio Perlasca was an Italian businessman who, posing as a Spanish diplomat in Budapest during the Holocaust, saved thousands of Hungarian Jews from deportation and death.
  • B. Maximilian Kolbe
    Maximilian Kolbe was a Polish Franciscan friar and Catholic priest who volunteered to die in place of another prisoner at Auschwitz, becoming a symbol of self-sacrificial love and martyrdom.
  • C. Raoul Wallenberg
    Raoul Wallenberg was a Swedish diplomat renowned for saving tens of thousands of Hungarian Jews from the Holocaust during World War II.
  • D. Romuald Racioppo
    Romuald Racioppo is a French author and illustrator best known for creating the children's superhero franchise that inspired the animated series "PJ Masks."
  • E. Jan Karski
    Jan Karski was a Polish World War II resistance courier and later academic renowned for bringing early eyewitness reports of the Holocaust to the Allied governments.
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02148c208190a882927905a861a6 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a854098c8190983d142c9930962b completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:08 p.m.