Triple

T11567881
Position Surface form Disambiguated ID Type / Status
Subject Peter Sissons E274301 entity
Predicate hasChild P369 FINISHED
Object Catherine Sissons
Catherine Sissons is the daughter of the late British television newsreader and journalist Peter Sissons.
E1029899 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: Catherine Sissons | Statement: [Peter Sissons, hasChild, Catherine Sissons]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catherine Sissons
Context triple: [Peter Sissons, hasChild, Catherine Sissons]
  • A. Catherine Hoskins
    Catherine Hoskins was an 18th-century English gentlewoman best known as the mother of William Cavendish, 4th Duke of Devonshire, a future Prime Minister of Great Britain.
  • B. Catherine McLeod
    Catherine McLeod was an American film and television actress active in the mid-20th century, known for her roles in dramas and thrillers.
  • C. Catherine Jenkins
    Catherine Jenkins is a Welsh mezzo-soprano singer and media personality known for her crossover classical and popular music performances.
  • D. Catherine Reynolds
    Catherine Reynolds is a notable individual distinguished enough to be recognized as a prominent bearer of the Reynolds surname.
  • E. Catherine Parker
    Catherine Parker was the wife of Sir John Perceval, 1st Earl of Egmont, and a member of the British aristocracy in the early 18th century.
  • 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: Catherine Sissons
Triple: [Peter Sissons, hasChild, Catherine Sissons]
Generated description
Catherine Sissons is the daughter of the late British television newsreader and journalist Peter Sissons.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Catherine Sissons
Target entity description: Catherine Sissons is the daughter of the late British television newsreader and journalist Peter Sissons.
  • A. Catherine Hoskins
    Catherine Hoskins was an 18th-century English gentlewoman best known as the mother of William Cavendish, 4th Duke of Devonshire, a future Prime Minister of Great Britain.
  • B. Catherine McLeod
    Catherine McLeod was an American film and television actress active in the mid-20th century, known for her roles in dramas and thrillers.
  • C. Catherine Jenkins
    Catherine Jenkins is a Welsh mezzo-soprano singer and media personality known for her crossover classical and popular music performances.
  • D. Catherine Reynolds
    Catherine Reynolds is a notable individual distinguished enough to be recognized as a prominent bearer of the Reynolds surname.
  • E. Catherine Parker
    Catherine Parker was the wife of Sir John Perceval, 1st Earl of Egmont, and a member of the British aristocracy in the early 18th century.
  • 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_69d6aae5ac3c81908d2b0a3a665665b2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88dd4305c8190ac5ff490b6b63e12 completed April 10, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a0e90e48190af6b802697d3256f completed May 3, 2026, 8:40 a.m.
NEDg Description generation batch_69f70c42d5008190bcd6275054637448 completed May 3, 2026, 8:50 a.m.
NED2 Entity disambiguation (via description) batch_69f70ce60a7081908f9498fcfec98e90 completed May 3, 2026, 8:52 a.m.
Created at: April 8, 2026, 9:37 p.m.