Triple

T3392505
Position Surface form Disambiguated ID Type / Status
Subject Washington, D.C. E71451 entity
Predicate hostsInstitution P186 FINISHED
Object National Archives and Records Administration E1026 NE FINISHED

How this triple was built (2 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: National Archives and Records Administration | Statement: [Washington, D.C., hostsInstitution, National Archives and Records Administration]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: National Archives and Records Administration
Context triple: [Washington, D.C., hostsInstitution, National Archives and Records Administration]
  • A. National Archives and Records Administration chosen
    The National Archives and Records Administration (NARA) is an independent U.S. federal agency responsible for preserving and providing access to the nation’s government records and historical documents.
  • B. The National Archives
    The National Archives is the official archive and publisher for the UK government, responsible for preserving and providing access to the nation’s historical and legal records.
  • C. National Personnel Records Center
    The National Personnel Records Center is a major U.S. federal facility responsible for storing and providing access to military and civilian personnel records.
  • D. 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.
  • E. Smithsonian Institution Archives
    The Smithsonian Institution Archives is the official repository that preserves and provides access to the historical records and institutional memory of the Smithsonian Institution.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad85a9c4a88190a854019341cb3b60 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb851e57c8190983cadcedc58db50 completed March 8, 2026, 5:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bc62c788190b6097e02601df386 completed March 12, 2026, 11:27 p.m.
Created at: March 8, 2026, 3:14 p.m.