Triple

T22644720
Position Surface form Disambiguated ID Type / Status
Subject Ostrower E558927 entity
Predicate hasNotableBearer P458 FINISHED
Object Fayga Ostrower 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: Fayga Ostrower | Statement: [Ostrower, hasNotableBearer, Fayga Ostrower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fayga Ostrower
Context triple: [Ostrower, hasNotableBearer, Fayga Ostrower]
  • A. Fayga Ostrower chosen
    Fayga Ostrower was a prominent Polish-born Brazilian artist, engraver, and art theorist known for her abstract works and influential writings on art and creativity.
  • B. Rivka Warhaftig
    Rivka Warhaftig was the wife of Israeli politician and religious Zionist leader Zerach Warhaftig.
  • C. Wanda Gershwitz
    Wanda Gershwitz is the seductive, cunning con artist at the center of the comedy film "A Fish Called Wanda," known for manipulating everyone around her to get her hands on stolen diamonds.
  • D. Batya Borowski
    Batya Borowski is the founder of the Bible Lands Museum in Jerusalem, an institution dedicated to the history and cultures of the ancient Near East.
  • E. Magda Bogin
    Magda Bogin is a literary translator and writer best known for her acclaimed English translation of Isabel Allende’s novel "The House of the Spirits."
  • 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_69e24547f7fc819086e2c4ba3b979657 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f170366ac881909e9d1dd2e7cf7a25 completed April 29, 2026, 2:43 a.m.
Created at: April 17, 2026, 3:05 p.m.