Triple

T3995
Position Surface form Disambiguated ID Type / Status
Subject Metropolitan Museum of Art E75 entity
Predicate hasDepartment P35 FINISHED
Object Department of Egyptian Art E75 NE FINISHED

How this triple was built (3 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: Department of Egyptian Art | Statement: [Metropolitan Museum of Art, hasDepartment, Department of Egyptian Art]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Department of Egyptian Art
Context triple: [Metropolitan Museum of Art, hasDepartment, Department of Egyptian Art]
  • A. Harvard Art Museums
    Harvard Art Museums is a renowned art institution in Cambridge, Massachusetts, comprising multiple museums and collections that support research, teaching, and public exhibitions.
  • B. Metropolitan Museum of Art chosen
    The Metropolitan Museum of Art is one of the world’s largest and most renowned art museums, housing an extensive collection spanning thousands of years and cultures.
  • C. John Rylands University Library
    John Rylands University Library is the main academic library of the University of Manchester, renowned for its extensive research collections and historic special holdings.
  • D. Sheffield Scientific School
    Sheffield Scientific School was Yale University's pioneering science and engineering school, instrumental in advancing scientific and technical education in the United States during the late 19th and early 20th centuries.
  • E. 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.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasDepartment
Context triple: [Metropolitan Museum of Art, hasDepartment, Department of Egyptian Art]
  • A. hasFaculty
    Indicates that an institution or department possesses or is associated with one or more faculty members.
  • B. hasPart chosen
    Indicates that one entity is a component, segment, or constituent part of another entity.
  • C. hasDivisionLevel
    Indicates that one entity is associated with a specific hierarchical or organizational division level of another entity.
  • D. hasAcademicStaff
    Indicates that an institution or organization employs or is associated with one or more academic staff members.
  • E. administeredBy
    Indicates that an action, service, or process is carried out, managed, or overseen by a specified agent or authority.
  • F. None of above.

Provenance (4 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_69a238d6b47881909e68288aed2fd858 completed Feb. 28, 2026, 12:37 a.m.
NER Named-entity recognition batch_69a23bcc8eb48190b897cc331563980a completed Feb. 28, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a23d871f1081909f1690b0fdf5afd0 completed Feb. 28, 2026, 12:57 a.m.
PD Predicate disambiguation batch_69a23994309081909ff3e869deef2156 completed Feb. 28, 2026, 12:40 a.m.
Created at: Feb. 28, 2026, 12:40 a.m.