Triple

T11049927
Position Surface form Disambiguated ID Type / Status
Subject Patty Duke E261218 entity
Predicate child P120 FINISHED
Object Kevin Pearce
Kevin Pearce is the son of Academy Award–winning actress Patty Duke.
E903499 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: Kevin Pearce | Statement: [Patty Duke, child, Kevin Pearce]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kevin Pearce
Context triple: [Patty Duke, child, Kevin Pearce]
  • A. Charlie Jeffery
    Charlie Jeffery is a British political scientist and academic leader who serves as Vice-Chancellor of the University of York.
  • B. Kyle Ward
    Kyle Ward is a screenwriter best known for penning the action film "Machete Kills."
  • C. Ewan Birney
    Ewan Birney is a British computational biologist best known for his leadership in the Human Genome Project and as director of the European Bioinformatics Institute (EMBL-EBI).
  • D. Shaun Martin
    Shaun Martin is a Grammy-winning American keyboardist, composer, and producer best known for his work with the jazz-fusion collective Snarky Puppy and his contributions to contemporary gospel and R&B music.
  • E. Chris Owen
    Chris Owen is an American character actor best known for his roles in films like the American Pie series and various teen comedies of the late 1990s and early 2000s.
  • 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: Kevin Pearce
Triple: [Patty Duke, child, Kevin Pearce]
Generated description
Kevin Pearce is the son of Academy Award–winning actress Patty Duke.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kevin Pearce
Target entity description: Kevin Pearce is the son of Academy Award–winning actress Patty Duke.
  • A. Charlie Jeffery
    Charlie Jeffery is a British political scientist and academic leader who serves as Vice-Chancellor of the University of York.
  • B. Kyle Ward
    Kyle Ward is a screenwriter best known for penning the action film "Machete Kills."
  • C. Ewan Birney
    Ewan Birney is a British computational biologist best known for his leadership in the Human Genome Project and as director of the European Bioinformatics Institute (EMBL-EBI).
  • D. Shaun Martin
    Shaun Martin is a Grammy-winning American keyboardist, composer, and producer best known for his work with the jazz-fusion collective Snarky Puppy and his contributions to contemporary gospel and R&B music.
  • E. Chris Owen
    Chris Owen is an American character actor best known for his roles in films like the American Pie series and various teen comedies of the late 1990s and early 2000s.
  • 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_69d6aa98650481908609c7c56bfa7902 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79868c78881908c8e3672c05ae7ec completed April 9, 2026, 12:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c851d5408190b12250a2a1322874 completed April 18, 2026, 6:07 p.m.
NEDg Description generation batch_69e3da8fbd388190898f4f52613543d3 completed April 18, 2026, 7:25 p.m.
NED2 Entity disambiguation (via description) batch_69e3dbbc784c8190a286bd5eb11bc44e completed April 18, 2026, 7:30 p.m.
Created at: April 8, 2026, 9:26 p.m.