Triple

T8724807
Position Surface form Disambiguated ID Type / Status
Subject Ed Bradley E207103 entity
Predicate spouse P13 FINISHED
Object Patricia Blanchet
Patricia Blanchet is the widow of renowned American broadcast journalist Ed Bradley, known for her connection to his legacy in television news.
E753005 NE FINISHED

How this triple was built (4 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: Patricia Blanchet | Statement: [Ed Bradley, spouse, Patricia Blanchet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patricia Blanchet
Context triple: [Ed Bradley, spouse, Patricia Blanchet]
  • A. Patricia Charbonnet
    Patricia Charbonnet is a film producer best known for her work on the influential 1995 comedy "Friday."
  • B. Jeanne Olivier
    Jeanne Olivier is known as the former spouse of American actor and author Christopher Lawford, a member of the Kennedy family.
  • C. Jeanne Martin
    Jeanne Martin was the wife of Lev Sedov, the revolutionary son of Russian Marxist leader Leon Trotsky.
  • D. Jeanne Rucar
    Jeanne Rucar was a French-born gymnast and memoirist best known as the longtime wife and confidante of Spanish filmmaker Luis Buñuel.
  • E. Judith Duchesne
    Judith Duchesne was a French colonial woman in New France best known as the mother of Charles Le Moyne de Longueuil et de Châteauguay, a prominent military officer and seigneur in early Canadian history.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Patricia Blanchet
Triple: [Ed Bradley, spouse, Patricia Blanchet]
Generated description
Patricia Blanchet is the widow of renowned American broadcast journalist Ed Bradley, known for her connection to his legacy in television news.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Patricia Blanchet
Target entity description: Patricia Blanchet is the widow of renowned American broadcast journalist Ed Bradley, known for her connection to his legacy in television news.
  • A. Patricia Charbonnet
    Patricia Charbonnet is a film producer best known for her work on the influential 1995 comedy "Friday."
  • B. Jeanne Olivier
    Jeanne Olivier is known as the former spouse of American actor and author Christopher Lawford, a member of the Kennedy family.
  • C. Jeanne Martin
    Jeanne Martin was the wife of Lev Sedov, the revolutionary son of Russian Marxist leader Leon Trotsky.
  • D. Jeanne Rucar
    Jeanne Rucar was a French-born gymnast and memoirist best known as the longtime wife and confidante of Spanish filmmaker Luis Buñuel.
  • E. Judith Duchesne
    Judith Duchesne was a French colonial woman in New France best known as the mother of Charles Le Moyne de Longueuil et de Châteauguay, a prominent military officer and seigneur in early Canadian history.
  • F. None of above. chosen

Provenance (5 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_69ca835811d8819081ea00fd2a2c9a1c completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d1404948190bc45d14a1ddb1a7e completed March 31, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf2908fec08190a286a082060a47bc completed April 3, 2026, 2:42 a.m.
NEDg Description generation batch_69cf2bd32cc881909ac8a61befa9929e completed April 3, 2026, 2:54 a.m.
NED2 Entity disambiguation (via description) batch_69cf2c69f83481909423858668d03a8b completed April 3, 2026, 2:56 a.m.
Created at: March 30, 2026, 6:36 p.m.