Triple

T13373229
Position Surface form Disambiguated ID Type / Status
Subject Brownstone E319118 entity
Predicate hasMember P10 FINISHED
Object Mimi Doby
Mimi Doby is a member of the Brownstone music group, contributing to their distinctive R&B sound.
E1036224 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: Mimi Doby | Statement: [Brownstone, hasMember, Mimi Doby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mimi Doby
Context triple: [Brownstone, hasMember, Mimi Doby]
  • A. Mimi Thompson
    Mimi Thompson is the wife of American pop artist James Rosenquist.
  • B. Mimi O'Donnell
    Mimi O'Donnell is an American costume designer, director, and producer best known for her long-term partnership with the late actor Philip Seymour Hoffman and her work in New York theater.
  • C. Mimi Parker
    Mimi Parker was an American drummer, vocalist, and co-founder of the indie rock band Low, known for her minimalist percussion and ethereal harmonies that helped define the group's slowcore sound.
  • D. Mimi Craven
    Mimi Craven is an American actress and former wife of horror filmmaker Wes Craven, known for her roles in film and television during the 1980s and 1990s.
  • E. Angelique Bates
    Angelique Bates is an American actress and comedian best known as an original cast member of the Nickelodeon sketch comedy series "All That."
  • 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: Mimi Doby
Triple: [Brownstone, hasMember, Mimi Doby]
Generated description
Mimi Doby is a member of the Brownstone music group, contributing to their distinctive R&B sound.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mimi Doby
Target entity description: Mimi Doby is a member of the Brownstone music group, contributing to their distinctive R&B sound.
  • A. Mimi Thompson
    Mimi Thompson is the wife of American pop artist James Rosenquist.
  • B. Mimi O'Donnell
    Mimi O'Donnell is an American costume designer, director, and producer best known for her long-term partnership with the late actor Philip Seymour Hoffman and her work in New York theater.
  • C. Mimi Parker
    Mimi Parker was an American drummer, vocalist, and co-founder of the indie rock band Low, known for her minimalist percussion and ethereal harmonies that helped define the group's slowcore sound.
  • D. Mimi Craven
    Mimi Craven is an American actress and former wife of horror filmmaker Wes Craven, known for her roles in film and television during the 1980s and 1990s.
  • E. Angelique Bates
    Angelique Bates is an American actress and comedian best known as an original cast member of the Nickelodeon sketch comedy series "All That."
  • 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_69d806b7bbac8190b85278c87fa7aff3 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dadcda64a48190b53243a763cd175b completed April 11, 2026, 11:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f72682c7f08190b8553ca22734df27 completed May 3, 2026, 10:42 a.m.
NEDg Description generation batch_69f7270bf9308190a3e9427ffce0e3ee completed May 3, 2026, 10:44 a.m.
NED2 Entity disambiguation (via description) batch_69f727d063c4819084b4990a0d759f79 completed May 3, 2026, 10:47 a.m.
Created at: April 9, 2026, 9:33 p.m.