Triple

T23520974
Position Surface form Disambiguated ID Type / Status
Subject FDLP E574504 entity
Predicate relatedTo P37 FINISHED
Object govinfo.gov NE NERFINISHED

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: govinfo.gov | Statement: [FDLP, relatedTo, govinfo.gov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: govinfo.gov
Context triple: [FDLP, relatedTo, govinfo.gov]
  • A. GovInfo.gov chosen
    GovInfo.gov is a U.S. Government Publishing Office website that provides free public access to official federal government publications, including legislative, executive, and judicial documents.
  • B. .gov
    .gov is the sponsored top-level domain primarily used by governmental entities in the United States.
  • C. USAspending.gov
    USAspending.gov is the official U.S. government website that provides public access to detailed data on federal spending, including contracts, grants, loans, and other financial assistance.
  • D. usa.gov
    usa.gov is the official U.S. government web portal that provides centralized access to government services, information, and resources for the public.
  • E. Office of the Federal Register
    The Office of the Federal Register is a U.S. government agency within the National Archives and Records Administration responsible for compiling, editing, and publishing official federal documents and regulations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245bb3dcc8190ba9a2b35972b58d0 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa85cb2c81908afbd0df0caeef4d completed April 29, 2026, 6:51 a.m.
Created at: April 17, 2026, 6:08 p.m.