Triple

T21615692
Position Surface form Disambiguated ID Type / Status
Subject Harry A. Blackmun Papers E533428 entity
Predicate heldBy P8 FINISHED
Object Manuscript Division of the Library of Congress
The Manuscript Division of the Library of Congress is a major archival repository that preserves and provides access to the personal papers and records of prominent individuals and organizations central to American history and culture.
E1492914 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: Manuscript Division of the Library of Congress | Statement: [Harry A. Blackmun Papers, heldBy, Manuscript Division of the Library of Congress]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manuscript Division of the Library of Congress
Context triple: [Harry A. Blackmun Papers, heldBy, Manuscript Division of the Library of Congress]
  • A. Manuscripts and Archives Division
    The Manuscripts and Archives Division is a research collection of the New York Public Library that preserves and provides access to primary source materials such as personal papers, organizational records, and historical documents.
  • B. Library of Congress Serial and Government Publications Division
    The Library of Congress Serial and Government Publications Division is the unit of the Library of Congress responsible for acquiring, preserving, and providing access to newspapers, periodicals, and government publications from the United States and around the world.
  • C. Library of Congress
    The Library of Congress is the national library of the United States and one of the world’s largest and most comprehensive research libraries, serving as the research arm of the U.S. Congress.
  • D. Library of Congress Policy and Standards Division
    The Library of Congress Policy and Standards Division is the unit within the Library of Congress responsible for developing, maintaining, and overseeing cataloging policies, standards, and classification systems used by libraries worldwide.
  • E. Manuscripts and Archives
    Manuscripts and Archives is a major special collections repository at Yale University that preserves and provides access to the university’s primary source materials, including historical manuscripts, institutional records, and personal papers.
  • 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: Manuscript Division of the Library of Congress
Triple: [Harry A. Blackmun Papers, heldBy, Manuscript Division of the Library of Congress]
Generated description
The Manuscript Division of the Library of Congress is a major archival repository that preserves and provides access to the personal papers and records of prominent individuals and organizations central to American history and culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Manuscript Division of the Library of Congress
Target entity description: The Manuscript Division of the Library of Congress is a major archival repository that preserves and provides access to the personal papers and records of prominent individuals and organizations central to American history and culture.
  • A. Manuscripts and Archives Division
    The Manuscripts and Archives Division is a research collection of the New York Public Library that preserves and provides access to primary source materials such as personal papers, organizational records, and historical documents.
  • B. Library of Congress Serial and Government Publications Division
    The Library of Congress Serial and Government Publications Division is the unit of the Library of Congress responsible for acquiring, preserving, and providing access to newspapers, periodicals, and government publications from the United States and around the world.
  • C. Library of Congress
    The Library of Congress is the national library of the United States and one of the world’s largest and most comprehensive research libraries, serving as the research arm of the U.S. Congress.
  • D. Library of Congress Policy and Standards Division
    The Library of Congress Policy and Standards Division is the unit within the Library of Congress responsible for developing, maintaining, and overseeing cataloging policies, standards, and classification systems used by libraries worldwide.
  • E. Manuscripts and Archives
    Manuscripts and Archives is a major special collections repository at Yale University that preserves and provides access to the university’s primary source materials, including historical manuscripts, institutional records, and personal papers.
  • 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_69e0c46411108190bba0d4176dffc9f3 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef3baab9e88190bc02f27133ef32d6 completed April 27, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09fd419ad48190a1a748a377f1a719 completed May 17, 2026, 5:39 p.m.
NEDg Description generation batch_6a09ff300f808190aa3c84c067b290bc completed May 17, 2026, 5:47 p.m.
NED2 Entity disambiguation (via description) batch_6a09ffc0c3f08190a2d386515223ec73 completed May 17, 2026, 5:49 p.m.
Created at: April 16, 2026, 6:33 p.m.