Triple

T1897136
Position Surface form Disambiguated ID Type / Status
Subject George Osborne E37607 entity
Predicate spouse P13 FINISHED
Object Frances Osborne
Frances Osborne is a British author and biographer known for works such as "The Bolter" and "Lilla's Feast."
E305377 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: Frances Osborne | Statement: [George Osborne, spouse, Frances Osborne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frances Osborne
Context triple: [George Osborne, spouse, Frances Osborne]
  • A. Thea Osborne
    Thea Osborne is a member of the Osborne family and the sister of British Conservative politician and former Chancellor of the Exchequer George Osborne.
  • B. Frances Rudge
    Frances Rudge was the wife of influential American film and theatre director Elia Kazan.
  • C. Frances Penney
    Frances Penney was the wife of Canadian physician and humanitarian Norman Bethune, accompanying parts of his medical and political journey in the early 20th century.
  • D. Estelle Winwood
    Estelle Winwood was a British-born stage and film actress known for her long career in theater and character roles in Hollywood, often playing eccentric or aristocratic older women.
  • E. Barbara Trentham
    Barbara Trentham was an American model and actress who later became a painter, known in part for her marriage to British comedian John Cleese.
  • 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: Frances Osborne
Triple: [George Osborne, spouse, Frances Osborne]
Generated description
Frances Osborne is a British author and biographer known for works such as "The Bolter" and "Lilla's Feast."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frances Osborne
Target entity description: Frances Osborne is a British author and biographer known for works such as "The Bolter" and "Lilla's Feast."
  • A. Thea Osborne
    Thea Osborne is a member of the Osborne family and the sister of British Conservative politician and former Chancellor of the Exchequer George Osborne.
  • B. Frances Rudge
    Frances Rudge was the wife of influential American film and theatre director Elia Kazan.
  • C. Frances Penney
    Frances Penney was the wife of Canadian physician and humanitarian Norman Bethune, accompanying parts of his medical and political journey in the early 20th century.
  • D. Estelle Winwood
    Estelle Winwood was a British-born stage and film actress known for her long career in theater and character roles in Hollywood, often playing eccentric or aristocratic older women.
  • E. Barbara Trentham
    Barbara Trentham was an American model and actress who later became a painter, known in part for her marriage to British comedian John Cleese.
  • 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_69a8861be7148190a680937ec451a304 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb16f416c8190a49b24523b3a7f85 completed March 7, 2026, 5:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01ce7643081908a1a939b9f4c1d59 completed March 10, 2026, 1:30 p.m.
NEDg Description generation batch_69b01def4f408190a0fcdba125b642bc completed March 10, 2026, 1:34 p.m.
NED2 Entity disambiguation (via description) batch_69b01e75d3c4819097fd86902eccd8c4 completed March 10, 2026, 1:36 p.m.
Created at: March 4, 2026, 7:35 p.m.