Triple

T17219695
Position Surface form Disambiguated ID Type / Status
Subject Richard Widmark E417941 entity
Predicate spouse P13 FINISHED
Object Susan Blanchard 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: Susan Blanchard | Statement: [Richard Widmark, spouse, Susan Blanchard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Blanchard
Context triple: [Richard Widmark, spouse, Susan Blanchard]
  • A. Susan Blanchard chosen
    Susan Blanchard is an American socialite and former Broadway production assistant best known as the third wife of actor Henry Fonda.
  • B. Rachel Blanchard
    Rachel Blanchard is a Canadian actress known for her roles in film and television, including the series "Clueless" and various comedy and drama projects.
  • C. Laura Bickford
    Laura Bickford is an American film producer best known for her work on acclaimed independent and studio films, including the Oscar-winning drama "Traffic."
  • D. Sisson Blanchard
    Sisson Blanchard is a Haitian naïve painter known for his vibrant, folkloric scenes that reflect rural life and cultural traditions in Haiti.
  • E. Susan Borman
    Susan Borman was the wife of Apollo 8 astronaut Frank Borman and a prominent figure among the early NASA astronaut wives, known for her role in supporting her husband’s career and coping with the stresses of the space program.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42ddc3cb88190a67e35164d710d9d completed April 19, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:38 a.m.