Triple

T13558063
Position Surface form Disambiguated ID Type / Status
Subject Leonid Pasternak E323830 entity
Predicate familyName P18 FINISHED
Object Pasternak E323830 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: Pasternak | Statement: [Leonid Pasternak, familyName, Pasternak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pasternak
Context triple: [Leonid Pasternak, familyName, Pasternak]
  • A. Boris Pasternak
    Boris Pasternak was a Russian poet and novelist best known internationally for his novel "Doctor Zhivago," which earned him the Nobel Prize in Literature in 1958.
  • B. Leonid Pasternak chosen
    Leonid Pasternak was a Russian Impressionist painter and illustrator known for his portraits and his association with the literary and artistic circles of late Imperial Russia.
  • C. Peter Pasternak
    Peter Pasternak is known primarily as the son of famed Hollywood film producer Joe Pasternak.
  • D. Joe Pasternak
    Joe Pasternak was a prominent Hollywood film producer best known for his successful musicals and light comedies from the 1930s through the 1950s.
  • E. Yuri Nagibin
    Yuri Nagibin was a prominent Soviet Russian writer and screenwriter known for his short stories and film scripts depicting wartime and postwar life.
  • 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_69d8076830b48190910a902bae5888e2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaff4223c8190801d153ae8f94c73 completed April 12, 2026, 2:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8c6cde08190b79fdcde8a81ccc4 completed May 3, 2026, 9:06 p.m.
Created at: April 9, 2026, 9:47 p.m.