Triple

T19888400
Position Surface form Disambiguated ID Type / Status
Subject Dexter Public Library E477963 entity
Predicate name P16 FINISHED
Object Dexter Public Library 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: Dexter Public Library | Statement: [Dexter Public Library, name, Dexter Public Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dexter Public Library
Context triple: [Dexter Public Library, name, Dexter Public Library]
  • A. Dexter Public Library chosen
    Dexter Public Library is a community library in Dexter, Maine, serving as a local center for reading, learning, and public events.
  • B. Dexter District Library
    Dexter District Library is a public library serving the residents of Dexter, Michigan, providing access to books, digital resources, and community programs.
  • C. Anderson Public Library
    Anderson Public Library is a public library system serving the residents of Anderson, Indiana, by providing access to books, digital resources, and community programs.
  • D. Leon Public Library
    Leon Public Library is a community library serving the residents of Leon, a small city in southern Iowa.
  • E. Jones Public Library
    Jones Public Library is the public library serving the community of Dayton, Texas, providing local residents with access to books, information resources, and community programs.
  • 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_69d8e51f32b08190b3687f4f60353250 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6590c1b9c8190abbfaa04b80713b3 completed April 20, 2026, 4:49 p.m.
Created at: April 10, 2026, 1:52 p.m.