Triple

T16047337
Position Surface form Disambiguated ID Type / Status
Subject Paul Green E389257 entity
Predicate fullName P16 FINISHED
Object Paul Gregory Green
Paul Gregory Green is an American football coach and former player best known for his involvement in collegiate and professional football programs.
E1190836 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: Paul Gregory Green | Statement: [Paul Green, fullName, Paul Gregory Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Gregory Green
Context triple: [Paul Green, fullName, Paul Gregory Green]
  • A. Christopher Greenup
    Christopher Greenup was an early American politician who served as the third governor of Kentucky in the early 19th century.
  • B. Paul Greer
    Paul Greer is a person notable enough to be specifically distinguished among individuals sharing the surname Greer.
  • C. Richard Green
    Richard Green was an American boxing referee best known for officiating major heavyweight bouts, including the 1980 title fight between Larry Holmes and Muhammad Ali.
  • D. Christopher Greenbury
    Christopher Greenbury was a British film editor best known for his Academy Award–winning work on the 1999 drama "American Beauty."
  • E. Andrew Green
    Andrew Green was a British paranormal investigator and author known for his extensive work on ghost hunting and psychical research.
  • 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: Paul Gregory Green
Triple: [Paul Green, fullName, Paul Gregory Green]
Generated description
Paul Gregory Green is an American football coach and former player best known for his involvement in collegiate and professional football programs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Paul Gregory Green
Target entity description: Paul Gregory Green is an American football coach and former player best known for his involvement in collegiate and professional football programs.
  • A. Christopher Greenup
    Christopher Greenup was an early American politician who served as the third governor of Kentucky in the early 19th century.
  • B. Paul Greer
    Paul Greer is a person notable enough to be specifically distinguished among individuals sharing the surname Greer.
  • C. Richard Green
    Richard Green was an American boxing referee best known for officiating major heavyweight bouts, including the 1980 title fight between Larry Holmes and Muhammad Ali.
  • D. Christopher Greenbury
    Christopher Greenbury was a British film editor best known for his Academy Award–winning work on the 1999 drama "American Beauty."
  • E. Andrew Green
    Andrew Green was a British paranormal investigator and author known for his extensive work on ghost hunting and psychical research.
  • 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1835eda348190aff492f0ff668cce completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbddc25481908fca660c4f14eaff completed May 10, 2026, 1:14 a.m.
NEDg Description generation batch_69ffdc915be88190a0e949fcee608242 completed May 10, 2026, 1:17 a.m.
NED2 Entity disambiguation (via description) batch_69ffdd17239c8190a3c0c4d146a279f7 completed May 10, 2026, 1:19 a.m.
Created at: April 10, 2026, 4:56 a.m.