Triple

T8468083
Position Surface form Disambiguated ID Type / Status
Subject 1910 United States Census E200212 entity
Predicate microdataSource P46377 FINISHED
Object Integrated Public Use Microdata Series E658766 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: Integrated Public Use Microdata Series | Statement: [1910 United States Census, microdataSource, Integrated Public Use Microdata Series]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Integrated Public Use Microdata Series
Context triple: [1910 United States Census, microdataSource, Integrated Public Use Microdata Series]
  • A. Medical Expenditure Panel Survey
    The Medical Expenditure Panel Survey is a large-scale, nationally representative U.S. survey that collects detailed data on healthcare use, costs, insurance coverage, and access to care for individuals and families.
  • B. Inter-university Consortium for Political and Social Research chosen
    The Inter-university Consortium for Political and Social Research (ICPSR) is a major international data archive and research organization that curates, preserves, and provides access to social and behavioral science data for researchers, instructors, and students.
  • C. American Community Survey
    The American Community Survey is an ongoing nationwide survey conducted by the U.S. Census Bureau that provides detailed annual demographic, social, economic, and housing data about the U.S. population.
  • D. U.S. Federal Statistical System
    The U.S. Federal Statistical System is the decentralized network of federal agencies responsible for collecting, analyzing, and disseminating official national statistics on the economy, population, health, and other key aspects of American life.
  • E. National Medical Expenditure Survey
    The National Medical Expenditure Survey was a large-scale U.S. government survey that collected detailed data on Americans’ health care use, costs, and insurance coverage, serving as a foundational source for health policy research.
  • 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: microdataSource
Context triple: [1910 United States Census, microdataSource, Integrated Public Use Microdata Series]
  • A. commonSources
    Indicates that two or more entities share the same origin, cause, or source.
  • B. mainSourceType
    Indicates the primary category or kind of source from which something originates or is derived.
  • C. hasMusicalSource
    Indicates that something derives from, is based on, or is influenced by a particular musical work or musical material.
  • D. museOf
    Indicates that one entity serves as the source of artistic or intellectual inspiration for another.
  • E. dataSourceFor chosen
    Indicates that one entity serves as the origin or provider of data that is used or consumed by another entity.
  • 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_69ca831a4f348190bfdd09250e86ae35 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe4d445f48190884df64bb1aebd41 completed March 31, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce39ead11c8190bf1524713a44a6fe completed April 2, 2026, 9:42 a.m.
PD Predicate disambiguation batch_69cbd10072cc819084be1ed9ac7ebe9d completed March 31, 2026, 1:49 p.m.
Created at: March 30, 2026, 6:11 p.m.