Triple

T20293471
Position Surface form Disambiguated ID Type / Status
Subject Tamsen Donner E510085 entity
Predicate relative P37 FINISHED
Object Georgia Donner 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: Georgia Donner | Statement: [Tamsen Donner, relative, Georgia Donner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgia Donner
Context triple: [Tamsen Donner, relative, Georgia Donner]
  • A. Frances Donner chosen
    Frances Donner was a young member of the ill-fated Donner Party, the group of American pioneers trapped in the Sierra Nevada during the winter of 1846–1847.
  • B. Ruth Nelson
    Ruth Nelson was an American stage and film actress known for her work with the Group Theatre and roles in classic mid-20th-century films.
  • C. Sonja Norwood
    Sonja Norwood is an American talent manager and television personality best known for managing the careers of her children, singer-actress Brandy and entertainer Ray J.
  • D. Helen Beth Duntz
    Helen Beth Duntz is known as the wife of American actor James MacArthur, who gained fame for his role as Danny "Danno" Williams on the television series "Hawaii Five-O."
  • E. Dorothy Yost
    Dorothy Yost was an American screenwriter active during Hollywood’s early sound era, known for contributing to numerous studio films across genres.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e67704262c8190bc903b733d849881 completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:13 a.m.