Triple

T3830505
Position Surface form Disambiguated ID Type / Status
Subject Windsor v. United States (in part) E90997 entity
Predicate counselForRespondent P51204 FINISHED
Object Roberta A. Kaplan
Roberta A. Kaplan is an American civil rights lawyer best known for successfully arguing the landmark Supreme Court case United States v. Windsor, which helped overturn the Defense of Marriage Act and advanced marriage equality in the United States.
E390640 NE FINISHED

How this triple was built (5 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: Roberta A. Kaplan | Statement: [Windsor v. United States (in part), counselForRespondent, Roberta A. Kaplan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roberta A. Kaplan
Context triple: [Windsor v. United States (in part), counselForRespondent, Roberta A. Kaplan]
  • A. Linda Pizzuti Henry
    Linda Pizzuti Henry is an American businesswoman and media executive, known for her leadership role at The Boston Globe and involvement in Fenway Sports Group.
  • B. Jennifer L. Mnookin
    Jennifer L. Mnookin is an American legal scholar and academic leader who serves as the chancellor of the University of Wisconsin–Madison.
  • C. Kathryn Reed Altman
    Kathryn Reed Altman was an American actress, documentarian, and archivist best known for preserving and promoting the legacy and work of her husband, filmmaker Robert Altman.
  • D. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • E. Judith R. Goodstein
    Judith R. Goodstein is an American historian of science and mathematics known for her work at Caltech, including authorship and editorial contributions to scholarly and institutional histories.
  • 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: Roberta A. Kaplan
Triple: [Windsor v. United States (in part), counselForRespondent, Roberta A. Kaplan]
Generated description
Roberta A. Kaplan is an American civil rights lawyer best known for successfully arguing the landmark Supreme Court case United States v. Windsor, which helped overturn the Defense of Marriage Act and advanced marriage equality in the United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roberta A. Kaplan
Target entity description: Roberta A. Kaplan is an American civil rights lawyer best known for successfully arguing the landmark Supreme Court case United States v. Windsor, which helped overturn the Defense of Marriage Act and advanced marriage equality in the United States.
  • A. Linda Pizzuti Henry
    Linda Pizzuti Henry is an American businesswoman and media executive, known for her leadership role at The Boston Globe and involvement in Fenway Sports Group.
  • B. Jennifer L. Mnookin
    Jennifer L. Mnookin is an American legal scholar and academic leader who serves as the chancellor of the University of Wisconsin–Madison.
  • C. Kathryn Reed Altman
    Kathryn Reed Altman was an American actress, documentarian, and archivist best known for preserving and promoting the legacy and work of her husband, filmmaker Robert Altman.
  • D. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • E. Judith R. Goodstein
    Judith R. Goodstein is an American historian of science and mathematics known for her work at Caltech, including authorship and editorial contributions to scholarly and institutional histories.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: counselForRespondent
Context triple: [Windsor v. United States (in part), counselForRespondent, Roberta A. Kaplan]
  • A. respondentPosition
    Indicates the role, title, or job position held by a respondent in the context of a survey, study, or inquiry.
  • B. respondentStatus
    Indicates the current role, condition, or state of a respondent in relation to a survey, inquiry, or legal/administrative process.
  • C. respondentRequirement
    Indicates that a particular condition, qualification, or obligation must be met by the respondent in order to participate in or complete the referenced activity or process.
  • D. hasCounsel chosen
    Indicates that one entity serves as a legal advisor or representative (counsel) for another entity.
  • E. defendant
    Indicates that an entity is the party accused or sued in a legal action or proceeding.
  • F. None of above.

Provenance (6 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_69aed960b538819096561c8ed448dec9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeeb86207c81908f40a01fe27f6a0b completed March 9, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb5628c481909c3b5ac59473a9cc completed March 14, 2026, 6:08 a.m.
NEDg Description generation batch_69b4fc08d65081908953482b10fa5611 completed March 14, 2026, 6:11 a.m.
NED2 Entity disambiguation (via description) batch_69b4fc7d8cf081909c4447818b5363c5 completed March 14, 2026, 6:13 a.m.
PD Predicate disambiguation batch_69aee74c2e04819094b94b3c0bac1806 completed March 9, 2026, 3:29 p.m.
Created at: March 9, 2026, 3:17 p.m.