Triple

T18176198
Position Surface form Disambiguated ID Type / Status
Subject Will Bruder E435165 entity
Predicate knownFor P22 FINISHED
Object Agave Library NE NERFINISHED

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: Agave Library | Statement: [Will Bruder, knownFor, Agave Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agave Library
Context triple: [Will Bruder, knownFor, Agave Library]
  • A. Stone Library
    Stone Library is a historic library building in Quincy, Massachusetts, that houses the personal book collection of the Adams family, including volumes owned by Presidents John Adams and John Quincy Adams.
  • B. Bibliotheca
    Bibliotheca is an ancient Greek mythographical handbook traditionally attributed to Apollodorus that compiles and summarizes a wide range of Greek myths and heroic legends.
  • C. Maag Library
    Maag Library is the main academic library of Youngstown State University, providing research resources, study spaces, and information services to its students and faculty.
  • D. Librarian’s Vault
    Librarian’s Vault is a secure, restricted-access chamber within the Library of Congress that houses some of the institution’s most rare, valuable, and historically significant materials.
  • E. Trible Library
    Trible Library is the main academic library at Christopher Newport University, providing students and faculty with research resources, study spaces, and academic support services.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Agave Library
Target entity description: Agave Library is a distinctive contemporary public library in Phoenix, Arizona, recognized for its innovative desert-inspired architecture designed by Will Bruder.
  • A. Stone Library
    Stone Library is a historic library building in Quincy, Massachusetts, that houses the personal book collection of the Adams family, including volumes owned by Presidents John Adams and John Quincy Adams.
  • B. Bibliotheca
    Bibliotheca is an ancient Greek mythographical handbook traditionally attributed to Apollodorus that compiles and summarizes a wide range of Greek myths and heroic legends.
  • C. Maag Library
    Maag Library is the main academic library of Youngstown State University, providing research resources, study spaces, and information services to its students and faculty.
  • D. Librarian’s Vault
    Librarian’s Vault is a secure, restricted-access chamber within the Library of Congress that houses some of the institution’s most rare, valuable, and historically significant materials.
  • E. Trible Library
    Trible Library is the main academic library at Christopher Newport University, providing students and faculty with research resources, study spaces, and academic support services.
  • F. None of above. chosen

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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df59bf3881909adc28cacbe9cb39 completed April 19, 2026, 1:57 p.m.
Created at: April 10, 2026, 10:30 a.m.