Triple

T13156147
Position Surface form Disambiguated ID Type / Status
Subject Nigel Stock E312594 entity
Predicate spouse P13 FINISHED
Object Sonia Williams
Sonia Williams is best known as the wife of British actor Nigel Stock.
E1024479 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: Sonia Williams | Statement: [Nigel Stock, spouse, Sonia Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonia Williams
Context triple: [Nigel Stock, spouse, Sonia Williams]
  • A. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • B. Leona Williams
    Leona Williams is an American country music singer and songwriter known for her work both as a solo artist and as a collaborator with major country stars.
  • C. Venessa Williams
    Venessa Williams is a notable individual who shares the Williams surname, recognized enough to be distinguished as a specific bearer of the name.
  • D. Fara Williams
    Fara Williams is an English former professional footballer and midfielder renowned as one of England’s most capped players and a key figure in the development of women’s football in the country.
  • E. Sheila Williams
    Sheila Williams is an acclaimed science fiction editor best known for her long tenure as editor of Asimov’s Science Fiction magazine.
  • 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: Sonia Williams
Triple: [Nigel Stock, spouse, Sonia Williams]
Generated description
Sonia Williams is best known as the wife of British actor Nigel Stock.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sonia Williams
Target entity description: Sonia Williams is best known as the wife of British actor Nigel Stock.
  • A. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • B. Leona Williams
    Leona Williams is an American country music singer and songwriter known for her work both as a solo artist and as a collaborator with major country stars.
  • C. Venessa Williams
    Venessa Williams is a notable individual who shares the Williams surname, recognized enough to be distinguished as a specific bearer of the name.
  • D. Fara Williams
    Fara Williams is an English former professional footballer and midfielder renowned as one of England’s most capped players and a key figure in the development of women’s football in the country.
  • E. Sheila Williams
    Sheila Williams is an acclaimed science fiction editor best known for her long tenure as editor of Asimov’s Science Fiction magazine.
  • 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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c06ccb881909390df18e1a6f7ed completed April 10, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eaf06f408190949f9ed5e899815b completed May 3, 2026, 6:28 a.m.
NEDg Description generation batch_69f6f07d52788190a39bc4fe049bcf5e completed May 3, 2026, 6:51 a.m.
NED2 Entity disambiguation (via description) batch_69f6f0d6eb2c81908463125a922edc9c completed May 3, 2026, 6:53 a.m.
Created at: April 9, 2026, 9:12 p.m.