Triple

T15343098
Position Surface form Disambiguated ID Type / Status
Subject Lee May E366846 entity
Predicate fullName P16 FINISHED
Object Lee Andrew May
Lee Andrew May is an American politician and former interim CEO of DeKalb County, Georgia, known for his role in local government leadership.
 E1151018 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: Lee Andrew May | Statement: [Lee May, fullName, Lee Andrew May]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lee Andrew May
Context triple: [Lee May, fullName, Lee Andrew May]
  • A. Robin Yount
    Robin Yount is a Hall of Fame former Major League Baseball shortstop and center fielder who spent his entire 20-year career with the Milwaukee Brewers and won two American League MVP awards.
  • B. Ulric Ellerhusen
    Ulric Ellerhusen was a German-American sculptor known for his architectural sculpture and public monuments in the early 20th century United States.
  • C. Alex Herron
    Alex Herron is a Norwegian music video and film director known for his work on numerous pop and rock videos as well as genre films.
  • D. Don Bailey
    Don Bailey is an architect best known for designing the Perth Concert Hall in Western Australia.
  • E. Dwight Hansen
    Dwight Hansen is the abusive and manipulative stepfather figure in Tobias Wolff’s memoir and its film adaptation "This Boy’s Life."
  • 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: Lee Andrew May
Triple: [Lee May, fullName, Lee Andrew May]
Generated description
Lee Andrew May is an American politician and former interim CEO of DeKalb County, Georgia, known for his role in local government leadership.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lee Andrew May
Target entity description: Lee Andrew May is an American politician and former interim CEO of DeKalb County, Georgia, known for his role in local government leadership.
  • A. Robin Yount
    Robin Yount is a Hall of Fame former Major League Baseball shortstop and center fielder who spent his entire 20-year career with the Milwaukee Brewers and won two American League MVP awards.
  • B. Ulric Ellerhusen
    Ulric Ellerhusen was a German-American sculptor known for his architectural sculpture and public monuments in the early 20th century United States.
  • C. Alex Herron
    Alex Herron is a Norwegian music video and film director known for his work on numerous pop and rock videos as well as genre films.
  • D. Don Bailey
    Don Bailey is an architect best known for designing the Perth Concert Hall in Western Australia.
  • E. Dwight Hansen
    Dwight Hansen is the abusive and manipulative stepfather figure in Tobias Wolff’s memoir and its film adaptation "This Boy’s Life."
  • 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_69d85a1355608190a6673ddb67231d54 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e14d8088190876fceca75d12322 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01f70e688190bb6a073e49ff968c completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff02745d1c819099f6261eced78dd0 completed May 9, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_69ff031d58048190852dae8a18981d35 completed May 9, 2026, 9:49 a.m.
Created at: April 10, 2026, 3:17 a.m.