Triple

T22529177
Position Surface form Disambiguated ID Type / Status
Subject Andersen Library E556986 entity
Predicate name P16 FINISHED
Object Andersen 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: Andersen Library | Statement: [Andersen Library, name, Andersen Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andersen Library
Context triple: [Andersen Library, name, Andersen Library]
  • A. Andersen Library chosen
    Andersen Library is the main academic library serving the students, faculty, and staff of the University of Wisconsin–Whitewater.
  • B. Hedberg Library
    Hedberg Library is the main academic library at Carthage College, providing students and faculty with research resources, study spaces, and information services.
  • C. Nunawading Library
    Nunawading Library is a public library and community hub in the Melbourne suburb of Nunawading, Victoria, offering lending services, study spaces, and local programs for residents.
  • D. Bernadotte Library
    The Bernadotte Library is a historic royal library in Stockholm that houses the Swedish royal family's extensive collection of books and manuscripts.
  • E. Tøyen Library
    Tøyen Library is a public library in the Tøyen neighborhood of Oslo, Norway, serving as a local cultural and educational hub for the community.
  • 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_69e11e57483c8190b0887c4f8ff26446 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ed5b5d081909d927f8aee44b673 completed April 29, 2026, 1:28 a.m.
Created at: April 16, 2026, 8:51 p.m.