Triple

T23086220
Position Surface form Disambiguated ID Type / Status
Subject Daughters of the American Revolution E575608 entity
Predicate foundedBy P104 FINISHED
Object Mary Desha 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: Mary Desha | Statement: [Daughters of the American Revolution, foundedBy, Mary Desha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Desha
Context triple: [Daughters of the American Revolution, foundedBy, Mary Desha]
  • A. Mary Desha chosen
    Mary Desha was an American educator and civic leader best known as one of the four co-founders of the patriotic lineage organization Daughters of the American Revolution.
  • B. Mary Katherine
    Mary Katherine is the adventurous teenage heroine of the animated fantasy film "Epic," who becomes shrunken and drawn into a hidden forest world where she helps defend nature from dark forces.
  • C. Mary Viola
    Mary Viola is a film producer known for her work on projects such as the sports drama "We Are Marshall."
  • D. Mary Tirony
    Mary Tirony is best known as the wife of American film and television actor Scott Brady.
  • E. Mary Catherine
    Mary Catherine is a central character in the indie film "Happythankyoumoreplease," portrayed as a young woman navigating love, friendship, and personal growth in New York City.
  • 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_69e245bf3e3c819086d3448720efc01b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18da573588190a8e0c859667e64a6 completed April 29, 2026, 4:48 a.m.
Created at: April 17, 2026, 3:57 p.m.