Triple

T5874956
Position Surface form Disambiguated ID Type / Status
Subject Ernő Goldfinger E130602 entity
Predicate spouse P13 FINISHED
Object Ursula Blackwell
Ursula Blackwell was a wealthy British heiress and art patron best known as the wife and collaborator of modernist architect Ernő Goldfinger.
 E553452 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: Ursula Blackwell | Statement: [Ernő Goldfinger, spouse, Ursula Blackwell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ursula Blackwell
Context triple: [Ernő Goldfinger, spouse, Ursula Blackwell]
  • A. Ursula Yale
    Ursula Yale was a daughter of Elihu Yale, the wealthy British-American merchant and philanthropist after whom Yale University is named.
  • B. Ursula Howells
    Ursula Howells was a British actress known for her work in film, television, and theatre during the mid-20th century.
  • C. Anne Ashmond
    Anne Ashmond is a fictional character appearing in the film "Royal Wedding."
  • D. Catherine Winslow
    Catherine Winslow is a central character in Terence Rattigan’s play "The Winslow Boy," portrayed as an intelligent and determined young woman who fights to clear her brother’s name in a public scandal.
  • E. Willa Weston
    Willa Weston is a driven and ambitious executive character in the comedy film "Fierce Creatures," known for her sharp wit and corporate savvy.
  • 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: Ursula Blackwell
Triple: [Ernő Goldfinger, spouse, Ursula Blackwell]
Generated description
Ursula Blackwell was a wealthy British heiress and art patron best known as the wife and collaborator of modernist architect Ernő Goldfinger.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ursula Blackwell
Target entity description: Ursula Blackwell was a wealthy British heiress and art patron best known as the wife and collaborator of modernist architect Ernő Goldfinger.
  • A. Ursula Yale
    Ursula Yale was a daughter of Elihu Yale, the wealthy British-American merchant and philanthropist after whom Yale University is named.
  • B. Ursula Howells
    Ursula Howells was a British actress known for her work in film, television, and theatre during the mid-20th century.
  • C. Anne Ashmond
    Anne Ashmond is a fictional character appearing in the film "Royal Wedding."
  • D. Catherine Winslow
    Catherine Winslow is a central character in Terence Rattigan’s play "The Winslow Boy," portrayed as an intelligent and determined young woman who fights to clear her brother’s name in a public scandal.
  • E. Willa Weston
    Willa Weston is a driven and ambitious executive character in the comedy film "Fierce Creatures," known for her sharp wit and corporate savvy.
  • 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_69c0085523688190bfd487479ce819e6 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c035fc86308190851b282456bcd715 completed March 22, 2026, 6:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b11b48d88190ba6cd5ade2f47a89 completed March 23, 2026, 3:18 a.m.
NEDg Description generation batch_69c0b1cc670081908c07c9f7c90afc2f completed March 23, 2026, 3:21 a.m.
NED2 Entity disambiguation (via description) batch_69c0b24d7d148190901e233d815d21ad completed March 23, 2026, 3:23 a.m.
Created at: March 22, 2026, 3:57 p.m.