Triple

T6658550
Position Surface form Disambiguated ID Type / Status
Subject UNC School of Law E151409 entity
Predicate hasNotableAlumni P51 FINISHED
Object Roy Cooper
Roy Cooper is an American attorney and Democratic politician serving as the Governor of North Carolina.
E609268 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: Roy Cooper | Statement: [UNC School of Law, hasNotableAlumni, Roy Cooper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roy Cooper
Context triple: [UNC School of Law, hasNotableAlumni, Roy Cooper]
  • A. Roy Cooper
    Roy Cooper is an actor known for appearing in the 1995 coming-of-age drama film "The Basketball Diaries."
  • B. Bob McDonnell
    Bob McDonnell is an American Republican politician and attorney who served as the 71st Governor of Virginia from 2010 to 2014.
  • C. Josh Hawley
    Josh Hawley is a conservative American politician and lawyer serving as the junior United States senator from Missouri.
  • D. Scott Edwards
    Scott Edwards is an Australian-born wicketkeeper-batsman who leads the Netherlands national cricket team in international competitions.
  • E. Jeremy Bulloch
    Jeremy Bulloch was an English actor best known for originating the role of Boba Fett in the original Star Wars trilogy.
  • 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: Roy Cooper
Triple: [UNC School of Law, hasNotableAlumni, Roy Cooper]
Generated description
Roy Cooper is an American attorney and Democratic politician serving as the Governor of North Carolina.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roy Cooper
Target entity description: Roy Cooper is an American attorney and Democratic politician serving as the Governor of North Carolina.
  • A. Roy Cooper
    Roy Cooper is an actor known for appearing in the 1995 coming-of-age drama film "The Basketball Diaries."
  • B. Bob McDonnell
    Bob McDonnell is an American Republican politician and attorney who served as the 71st Governor of Virginia from 2010 to 2014.
  • C. Josh Hawley
    Josh Hawley is a conservative American politician and lawyer serving as the junior United States senator from Missouri.
  • D. Scott Edwards
    Scott Edwards is an Australian-born wicketkeeper-batsman who leads the Netherlands national cricket team in international competitions.
  • E. Jeremy Bulloch
    Jeremy Bulloch was an English actor best known for originating the role of Boba Fett in the original Star Wars trilogy.
  • 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_69c687f5fac48190a09e4838d9c6b45d completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b0706514819087270d1c68866e2c completed March 27, 2026, 4:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6ef04fe608190b34cc53a54318826 completed March 27, 2026, 8:56 p.m.
NEDg Description generation batch_69c6f0a2a150819091ec6e6d2905abcb completed March 27, 2026, 9:03 p.m.
NED2 Entity disambiguation (via description) batch_69c6f1344dd4819096c1d3e216320c4d completed March 27, 2026, 9:05 p.m.
Created at: March 27, 2026, 2:01 p.m.