Triple

T9337573
Position Surface form Disambiguated ID Type / Status
Subject Kwame E224682 entity
Predicate isNameOf P744 FINISHED
Object Kwame R. Brown
Kwame R. Brown is an American politician who served as the chairman of the Council of the District of Columbia before resigning amid a federal bank fraud investigation.
 E794244 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: Kwame R. Brown | Statement: [Kwame, isNameOf, Kwame R. Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kwame R. Brown
Context triple: [Kwame, isNameOf, Kwame R. Brown]
  • A. Anthony G. Brown
    Anthony G. Brown is an American politician and lawyer who has served as Maryland’s attorney general and previously as the state’s lieutenant governor and a U.S. congressman.
  • B. Jelani Kilpatrick
    Jelani Kilpatrick is known as one of the sons of former Detroit mayor Kwame Kilpatrick.
  • C. Kwame Harris
    Kwame Harris is a former American football offensive tackle who played in the NFL, primarily for the San Francisco 49ers and Oakland Raiders.
  • D. Hassan Johnson
    Hassan Johnson is an American actor best known for his roles in the film "Belly" and the HBO series "The Wire."
  • E. Frank Reicher
    Frank Reicher was a German-American actor and director best known for his roles in early Hollywood films, including classic monster movies of the 1930s.
  • 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: Kwame R. Brown
Triple: [Kwame, isNameOf, Kwame R. Brown]
Generated description
Kwame R. Brown is an American politician who served as the chairman of the Council of the District of Columbia before resigning amid a federal bank fraud investigation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kwame R. Brown
Target entity description: Kwame R. Brown is an American politician who served as the chairman of the Council of the District of Columbia before resigning amid a federal bank fraud investigation.
  • A. Anthony G. Brown
    Anthony G. Brown is an American politician and lawyer who has served as Maryland’s attorney general and previously as the state’s lieutenant governor and a U.S. congressman.
  • B. Jelani Kilpatrick
    Jelani Kilpatrick is known as one of the sons of former Detroit mayor Kwame Kilpatrick.
  • C. Kwame Harris
    Kwame Harris is a former American football offensive tackle who played in the NFL, primarily for the San Francisco 49ers and Oakland Raiders.
  • D. Hassan Johnson
    Hassan Johnson is an American actor best known for his roles in the film "Belly" and the HBO series "The Wire."
  • E. Frank Reicher
    Frank Reicher was a German-American actor and director best known for his roles in early Hollywood films, including classic monster movies of the 1930s.
  • 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_69ca84286fcc81909f6e7fd7a7e862a2 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd37f312408190b5501432a6a855b7 completed April 1, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0f3b37b408190957c371233d8a3bd completed April 4, 2026, 11:19 a.m.
NEDg Description generation batch_69d0f4b346988190b70cd311dc3481cd completed April 4, 2026, 11:23 a.m.
NED2 Entity disambiguation (via description) batch_69d0f589b86c8190a68c7047766ce464 completed April 4, 2026, 11:27 a.m.
Created at: March 30, 2026, 7:40 p.m.