Triple

T16844035
Position Surface form Disambiguated ID Type / Status
Subject Roy Grace E409488 entity
Predicate spouse P13 FINISHED
Object Sandy
Sandy is the estranged wife of Detective Superintendent Roy Grace in Peter James’s crime novel series.
E1237159 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: Sandy | Statement: [Roy Grace, spouse, Sandy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandy
Context triple: [Roy Grace, spouse, Sandy]
  • A. Sandy
    Sandy is a common nickname or short form of the given name Alexander.
  • B. Sandy
    Sandy is a fictional character from Mark Twain’s satirical novel "A Connecticut Yankee in King Arthur’s Court," known as a medieval woman who becomes the companion and later wife of the time-traveling protagonist.
  • C. Sandy
    Sandy is a suburban city in the Salt Lake City metropolitan area of Utah, known for its residential communities and proximity to outdoor recreation in the nearby Wasatch Mountains.
  • D. Sandy
    Sandy is a central character in the story featuring Annie, often portrayed as her loyal and beloved dog companion.
  • E. Sandy
    Sandy is the commonly used nickname of Sandy Brondello, an Australian former professional basketball player and current WNBA head coach.
  • 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: Sandy
Triple: [Roy Grace, spouse, Sandy]
Generated description
Sandy is the estranged wife of Detective Superintendent Roy Grace in Peter James’s crime novel series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sandy
Target entity description: Sandy is the estranged wife of Detective Superintendent Roy Grace in Peter James’s crime novel series.
  • A. Sandy
    Sandy is a fictional character from Mark Twain’s satirical novel "A Connecticut Yankee in King Arthur’s Court," known as a medieval woman who becomes the companion and later wife of the time-traveling protagonist.
  • B. Sandy
    Sandy is a central female character in the 1971 film "Carnal Knowledge," representing one of the key romantic relationships that illuminate the protagonists’ evolving attitudes toward sex and intimacy.
  • C. Sandy
    Sandy is a central character in the story featuring Annie, often portrayed as her loyal and beloved dog companion.
  • D. Sandy
    Sandy is a common nickname or short form of the given name Alexander.
  • E. Sandy
    Sandy is the commonly used nickname of Sandy Brondello, an Australian former professional basketball player and current WNBA head coach.
  • 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_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b3533a9481909730571e6f758cbe completed April 18, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb1b47648190909eaaf4e1e8e4c3 completed May 10, 2026, 5:06 p.m.
NEDg Description generation batch_6a00bc22dc1c81909edc5cdb239f0ea8 completed May 10, 2026, 5:10 p.m.
NED2 Entity disambiguation (via description) batch_6a00bce879648190acbd5645cd1a4ec8 completed May 10, 2026, 5:14 p.m.
Created at: April 10, 2026, 5:24 a.m.