Triple

T21089879
Position Surface form Disambiguated ID Type / Status
Subject Sonny Perdue E519607 entity
Predicate givenName P17 FINISHED
Object George
George is the first name of Sonny Perdue, the American politician who served as U.S. Secretary of Agriculture and former Governor of Georgia.
E1466225 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: George | Statement: [Sonny Perdue, givenName, George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George
Context triple: [Sonny Perdue, givenName, George]
  • A. George
    George is the given name of George Habash, the Palestinian Christian physician and founder of the Popular Front for the Liberation of Palestine.
  • B. George
    George is the given first name of the American gangster Bugs Moran, a prominent Prohibition-era mobster in Chicago.
  • C. George
    George is the given name of the British historian George Macaulay Trevelyan, known for his influential works on English and Italian history.
  • D. George
    George is the given name of George North, 3rd Earl of Guilford, a British peer from the late 18th and early 19th centuries.
  • E. George
    George is the given name of George Winslow, an American child actor known for his distinctive raspy voice in 1950s films.
  • 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: George
Triple: [Sonny Perdue, givenName, George]
Generated description
George is the first name of Sonny Perdue, the American politician who served as U.S. Secretary of Agriculture and former Governor of Georgia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: George
Target entity description: George is the first name of Sonny Perdue, the American politician who served as U.S. Secretary of Agriculture and former Governor of Georgia.
  • A. George
    George is the first name of George Rockingham Gilmer, a 19th-century American politician who served as governor of Georgia.
  • B. George
    George is the birth name of Rex Bell, an American actor and politician who served as the 21st Lieutenant Governor of Nevada.
  • C. George
    George is the given name of George W. Norris, a prominent early 20th-century American politician known for his progressive reforms and long service in the U.S. Congress.
  • D. George
    George is the first name of George Strait, the American country music singer known as the "King of Country."
  • E. George
    George is the given name of George Wallace Jones, a 19th-century American politician and U.S. senator from Iowa.
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7094dd65481909391ed74115afc23 completed April 21, 2026, 5:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a095a5879d88190ac29a01da51ea009 completed May 17, 2026, 6:04 a.m.
NEDg Description generation batch_6a095c017bec81909fd6c73a0fb677df completed May 17, 2026, 6:11 a.m.
NED2 Entity disambiguation (via description) batch_6a095cee4c308190a08844f285231ff9 completed May 17, 2026, 6:15 a.m.
Created at: April 16, 2026, 2:50 p.m.