Triple

T20104588
Position Surface form Disambiguated ID Type / Status
Subject Ida Straus E486963 entity
Predicate child P120 FINISHED
Object Sara Straus 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: Sara Straus | Statement: [Ida Straus, child, Sara Straus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Straus
Context triple: [Ida Straus, child, Sara Straus]
  • A. Sara Straus chosen
    Sara Straus was the mother of American merchant and philanthropist Nathan Straus, a key figure in the prominent Straus family associated with Macy’s and social reform.
  • B. Rose Schlossberg
    Rose Schlossberg is an American actress, comedian, and web series creator, and the eldest grandchild of former U.S. President John F. Kennedy.
  • C. Carolyn Strauss
    Carolyn Strauss is an American television executive and producer best known for her influential work at HBO, including helping develop and produce acclaimed series such as Game of Thrones.
  • D. Sylvia Straus
    Sylvia Straus was a concert pianist and music educator best known as the wife and intellectual partner of Jewish theologian Abraham Joshua Heschel.
  • E. June Preisser
    June Preisser was an American film actress and dancer best known for her energetic supporting roles in 1930s and 1940s Hollywood musicals, often playing peppy, acrobatic teenagers.
  • 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666daf73c819089f02ca6faa2c283 completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:27 p.m.