Triple

T437076
Position Surface form Disambiguated ID Type / Status
Subject Milwaukee E10031 entity
Predicate hasMayor P185 FINISHED
Object Cavalier Johnson
Cavalier Johnson is an American politician who serves as the mayor of Milwaukee, Wisconsin.
E57505 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: Cavalier Johnson | Statement: [Milwaukee, hasMayor, Cavalier Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cavalier Johnson
Context triple: [Milwaukee, hasMayor, Cavalier Johnson]
  • A. Christopher Johnson
    Christopher Johnson is an American businessman and member of the Johnson family who serves as a principal owner and executive of the New York Jets NFL franchise.
  • B. Patrick Carr
    Patrick Carr was one of the five colonists fatally wounded in the 1770 Boston Massacre, whose death helped inflame anti-British sentiment in the American colonies.
  • C. Jules Irving
    Jules Irving was an influential American theater director, producer, and co-founder of the San Francisco Actor's Workshop who later led New York's Lincoln Center Repertory Company.
  • D. DeVon Harris
    DeVon Harris is a songwriter best known for his work on the track "So High."
  • E. Jamal Greene
    Jamal Greene is a prominent American constitutional law scholar and professor known for his work on rights adjudication and the interpretation of the U.S. Constitution.
  • 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: Cavalier Johnson
Triple: [Milwaukee, hasMayor, Cavalier Johnson]
Generated description
Cavalier Johnson is an American politician who serves as the mayor of Milwaukee, Wisconsin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cavalier Johnson
Target entity description: Cavalier Johnson is an American politician who serves as the mayor of Milwaukee, Wisconsin.
  • A. Christopher Johnson
    Christopher Johnson is an American businessman and member of the Johnson family who serves as a principal owner and executive of the New York Jets NFL franchise.
  • B. Patrick Carr
    Patrick Carr was one of the five colonists fatally wounded in the 1770 Boston Massacre, whose death helped inflame anti-British sentiment in the American colonies.
  • C. Jules Irving
    Jules Irving was an influential American theater director, producer, and co-founder of the San Francisco Actor's Workshop who later led New York's Lincoln Center Repertory Company.
  • D. DeVon Harris
    DeVon Harris is a songwriter best known for his work on the track "So High."
  • E. Jamal Greene
    Jamal Greene is a prominent American constitutional law scholar and professor known for his work on rights adjudication and the interpretation of the U.S. Constitution.
  • 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_69a2e8465ef481909655c681b01e2986 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2ef0c97188190b62104cb639d4b60 completed Feb. 28, 2026, 1:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69a44f522acc81909d16527bd08e458d completed March 1, 2026, 2:38 p.m.
NEDg Description generation batch_69a44fd970d881909ed3ae28debf4760 completed March 1, 2026, 2:40 p.m.
NED2 Entity disambiguation (via description) batch_69a4506c3d4881908eb97e489e4b9078 completed March 1, 2026, 2:42 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.