Triple

T12385730
Position Surface form Disambiguated ID Type / Status
Subject Geoffrey Unsworth E295858 entity
Predicate spouse P13 FINISHED
Object Maggie Unsworth
Maggie Unsworth was the wife of acclaimed British cinematographer Geoffrey Unsworth, known primarily in relation to his life and career.
 E979400 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: Maggie Unsworth | Statement: [Geoffrey Unsworth, spouse, Maggie Unsworth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maggie Unsworth
Context triple: [Geoffrey Unsworth, spouse, Maggie Unsworth]
  • A. Lesley Walker
    Lesley Walker is a British film editor known for her work on numerous feature films, including the 2002 adaptation of "Nicholas Nickleby."
  • B. Maggie Ansell
    Maggie Ansell is a screenwriter known for her work on the biographical film "The Life and Death of Peter Sellers."
  • C. Sarah Etheridge
    Sarah Etheridge was the wife of prominent American financier and U.S. Secretary of the Treasury Lyman J. Gage.
  • D. Laura Mennell
    Laura Mennell is a Canadian actress known for her roles in science fiction and fantasy film and television, including appearances in projects like Watchmen and the series Alphas.
  • E. Lucinda Coxon
    Lucinda Coxon is a British playwright and screenwriter known for her work on films such as "The Danish Girl" and various stage adaptations.
  • 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: Maggie Unsworth
Triple: [Geoffrey Unsworth, spouse, Maggie Unsworth]
Generated description
Maggie Unsworth was the wife of acclaimed British cinematographer Geoffrey Unsworth, known primarily in relation to his life and career.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maggie Unsworth
Target entity description: Maggie Unsworth was the wife of acclaimed British cinematographer Geoffrey Unsworth, known primarily in relation to his life and career.
  • A. Lesley Walker
    Lesley Walker is a British film editor known for her work on numerous feature films, including the 2002 adaptation of "Nicholas Nickleby."
  • B. Maggie Ansell
    Maggie Ansell is a screenwriter known for her work on the biographical film "The Life and Death of Peter Sellers."
  • C. Sarah Etheridge
    Sarah Etheridge was the wife of prominent American financier and U.S. Secretary of the Treasury Lyman J. Gage.
  • D. Laura Mennell
    Laura Mennell is a Canadian actress known for her roles in science fiction and fantasy film and television, including appearances in projects like Watchmen and the series Alphas.
  • E. Lucinda Coxon
    Lucinda Coxon is a British playwright and screenwriter known for her work on films such as "The Danish Girl" and various stage adaptations.
  • 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fbd489c819098233a111442762e completed April 10, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62ac939bc819081629b9eef20c4e7 completed May 2, 2026, 4:48 p.m.
NEDg Description generation batch_69f62c7b28588190839c35c19856d16f completed May 2, 2026, 4:55 p.m.
NED2 Entity disambiguation (via description) batch_69f62e403a308190a2bba3fefc420932 completed May 2, 2026, 5:02 p.m.
Created at: April 8, 2026, 9:54 p.m.