Triple

T16790702
Position Surface form Disambiguated ID Type / Status
Subject Darryl W. Perry E408100 entity
Predicate familyName P18 FINISHED
Object Perry
Perry is a common English surname borne by numerous notable individuals across politics, entertainment, sports, and other fields.
E60656 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: Perry | Statement: [Darryl W. Perry, familyName, Perry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perry
Context triple: [Darryl W. Perry, familyName, Perry]
  • A. John
    John is the given first name of the legendary American professional golfer Byron Nelson, one of the sport’s early great champions.
  • B. John
    John is the given name of Sir John Byron, an English nobleman and Royalist commander during the English Civil War.
  • C. John
    John is the first name of American college football coach Jimbo Fisher, known for leading Florida State University to a national championship.
  • D. John
    John "Johnny" Weir is an American figure skater and television commentator known for his artistic style on the ice and flamboyant public persona.
  • E. John
    John J. McCloy was an influential American lawyer, banker, and statesman who served in key roles such as U.S. High Commissioner for Germany and president of the World Bank.
  • 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: Perry
Triple: [Darryl W. Perry, familyName, Perry]
Generated description
Perry is a common English surname borne by numerous notable individuals across politics, entertainment, sports, and other fields.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Perry
Target entity description: Perry is a common English surname borne by numerous notable individuals across politics, entertainment, sports, and other fields.
  • A. Perry chosen
    Perry is a common English surname borne by numerous notable individuals across politics, arts, sports, and other fields.
  • B. Perry
    Perry is a fictional character played by British comedian and actress Katherine Lucy Bridget Burke, best known for her work in television comedy.
  • C. Perry
    Perry is one of the two socially awkward teenage protagonists in the British comedy film "Kevin & Perry Go Large," known for his obsession with clubbing, DJ culture, and losing his virginity.
  • D. Perry
    Perry is the central character in the film "Makers," around whom the story’s main events and themes revolve.
  • E. Perry
    Perry is a small city in northern Utah, United States, known for its rural character and proximity to the Wasatch Mountains and Great Salt Lake.
  • F. None of above.

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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a5d10c8190a581de79e4f7ccfa completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab0c39108190a332fdc78c053628 completed May 10, 2026, 3:58 p.m.
NEDg Description generation batch_6a00ac621b3881908887b640bf3e3fce completed May 10, 2026, 4:03 p.m.
NED2 Entity disambiguation (via description) batch_6a00acc3a9dc819087e07e539760bf34 completed May 10, 2026, 4:05 p.m.
Created at: April 10, 2026, 5:22 a.m.