Triple

T10217753
Position Surface form Disambiguated ID Type / Status
Subject Sarah, Duchess of York E242490 entity
Predicate givenName P17 FINISHED
Object Sarah
Sarah, Duchess of York is a British author, media personality, and former member of the British royal family who was previously married to Prince Andrew, Duke of York.
E850757 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: Sarah | Statement: [Sarah, Duchess of York, givenName, Sarah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah
Context triple: [Sarah, Duchess of York, givenName, Sarah]
  • A. Sarah
    Sarah is a recurring character in the animated television series "Ed, Edd n Eddy," known as Ed's bossy, temperamental younger sister.
  • B. Sarah
    Sarah is the resilient and traumatized protagonist of the British horror film "The Descent," known for her harrowing journey through monster-infested caves.
  • C. Sarah
    Sarah is the given first name of the actress and comedian Patsy Kelly.
  • D. Sarah
    Sarah is the given name of American actress Sarah Paulson, known for her versatile roles in film and television, particularly in "American Horror Story" and "The People v. O. J. Simpson."
  • E. Sarah
    Sarah is the given name of Sarah P. Duke, the philanthropist and namesake of Duke University's Sarah P. Duke Gardens.
  • 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: Sarah
Triple: [Sarah, Duchess of York, givenName, Sarah]
Generated description
Sarah, Duchess of York is a British author, media personality, and former member of the British royal family who was previously married to Prince Andrew, Duke of York.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarah
Target entity description: Sarah, Duchess of York is a British author, media personality, and former member of the British royal family who was previously married to Prince Andrew, Duke of York.
  • A. Sarah
    Sarah, Lady McCorquodale is a British aristocrat best known as the elder sister of Diana, Princess of Wales, and for her work in public service and charitable activities.
  • B. Sarah
    Sarah is a person whose full name is Clare Sarah Branson.
  • C. Sarah
    Sarah is a person whose full name is Sarah Catherine McPherson Risher Getty.
  • D. Sarah
    Sarah is the given name of Sarah Jane Negley Mellon, a prominent American socialite and philanthropist from the influential Mellon family.
  • E. Sarah
    Sarah is the first name of Sally Jewell, the former U.S. Secretary of the Interior and business executive.
  • 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d3aa6fcf6c81908a589585bbd48ab8 completed April 6, 2026, 12:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d6a8142f948190b19e3c1f70f6430f completed April 8, 2026, 7:10 p.m.
NEDg Description generation batch_69d6d0003434819093e3f82a556db79c completed April 8, 2026, 10 p.m.
NED2 Entity disambiguation (via description) batch_69d6df3c8f748190923db41ef1a9a03a completed April 8, 2026, 11:05 p.m.
Created at: April 6, 2026, 11:07 a.m.