Triple

T2166847
Position Surface form Disambiguated ID Type / Status
Subject Tamara Geva E46928 entity
Predicate name P16 FINISHED
Object Tamara Geva E46928 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: Tamara Geva | Statement: [Tamara Geva, name, Tamara Geva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tamara Geva
Context triple: [Tamara Geva, name, Tamara Geva]
  • A. Tamara Geva chosen
    Tamara Geva was a Russian-American dancer and actress known for her early collaborations with choreographer George Balanchine and her influential work on Broadway and in modern ballet.
  • B. Tatiana Schlossberg
    Tatiana Schlossberg is an American journalist and author, known for her environmental reporting and as a member of the Kennedy family.
  • C. Sonya Levien
    Sonya Levien was a prominent American screenwriter known for her work on numerous Hollywood films from the silent era through the 1950s, often adapting literary and theatrical works for the screen.
  • D. Julia Bloch
    Julia Bloch is an American poet, editor, and scholar known for her innovative work in contemporary poetry and literary criticism.
  • E. Lauretta Geigerman
    Lauretta Geigerman was the wife of American mob boss Frank Costello, a prominent figure in mid-20th-century organized crime.
  • 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_69a88a184cbc8190877791f6552c2484 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbeab223881908aaa2bc4f85329cc completed March 7, 2026, 5:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6538c750819093d2e3f8e5f66a63 completed March 9, 2026, 6:14 a.m.
Created at: March 4, 2026, 7:45 p.m.