Triple

T4857166
Position Surface form Disambiguated ID Type / Status
Subject Paul Scofield E108563 entity
Predicate spouse P13 FINISHED
Object Joy Parker
Joy Parker was the wife of acclaimed English actor Paul Scofield, with whom she shared a long marriage and family life.
 E475156 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: Joy Parker | Statement: [Paul Scofield, spouse, Joy Parker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Joy Parker
Context triple: [Paul Scofield, spouse, Joy Parker]
  • A. Carol Parker
    Carol Parker is best known as the wife of Marlon Jackson, a member of the famed Jackson family and former singer of The Jackson 5.
  • B. Kim Parker
    Kim Parker is a comedic, outspoken teenage character from the sitcom "Moesha," later becoming a central figure in its spin-off series "The Parkers."
  • C. Jean Parker
    Jean Parker was an American film and stage actress best known for her roles in 1930s Hollywood productions, including the adaptation of "Little Women."
  • D. Jennifer Parker
    Jennifer Parker is Marty McFly’s girlfriend in the Back to the Future film series, appearing as a key supporting character across its time-travel adventures.
  • E. Tej Parker
    Tej Parker is a tech-savvy mechanic and hacker in the Fast & Furious film franchise, known for his intelligence, humor, and close partnership with Roman Pearce.
  • 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: Joy Parker
Triple: [Paul Scofield, spouse, Joy Parker]
Generated description
Joy Parker was the wife of acclaimed English actor Paul Scofield, with whom she shared a long marriage and family life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Joy Parker
Target entity description: Joy Parker was the wife of acclaimed English actor Paul Scofield, with whom she shared a long marriage and family life.
  • A. Carol Parker
    Carol Parker is best known as the wife of Marlon Jackson, a member of the famed Jackson family and former singer of The Jackson 5.
  • B. Kim Parker
    Kim Parker is a comedic, outspoken teenage character from the sitcom "Moesha," later becoming a central figure in its spin-off series "The Parkers."
  • C. Jean Parker
    Jean Parker was an American film and stage actress best known for her roles in 1930s Hollywood productions, including the adaptation of "Little Women."
  • D. Jennifer Parker
    Jennifer Parker is Marty McFly’s girlfriend in the Back to the Future film series, appearing as a key supporting character across its time-travel adventures.
  • E. Tej Parker
    Tej Parker is a tech-savvy mechanic and hacker in the Fast & Furious film franchise, known for his intelligence, humor, and close partnership with Roman Pearce.
  • 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_69bd440a89548190a5f14ba6da6b97dc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d3f24688190b2f2b79bcde96973 completed March 20, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5cec638481909a3345f348116bbc completed March 21, 2026, 8:55 a.m.
NEDg Description generation batch_69be5fd0ec648190842438a3235481e5 completed March 21, 2026, 9:07 a.m.
NED2 Entity disambiguation (via description) batch_69be606f82e88190b2b1501ec83b33af completed March 21, 2026, 9:10 a.m.
Created at: March 20, 2026, 1:26 p.m.