Triple

T2939001
Position Surface form Disambiguated ID Type / Status
Subject Frost Library E79338 entity
Predicate name P16 FINISHED
Object Frost Library E79338 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: Frost Library | Statement: [Frost Library, name, Frost Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frost Library
Context triple: [Frost Library, name, Frost Library]
  • A. Frost Library chosen
    Frost Library is the main academic library at Amherst College, housing extensive research collections and study spaces for students and faculty.
  • B. Vollum Library
    Vollum Library is the main academic library at Reed College in Portland, Oregon, supporting the college’s undergraduate liberal arts and research programs.
  • C. Raether Library
    Raether Library is the main academic library and information technology hub of Trinity College in Hartford, Connecticut, supporting the college’s research, teaching, and learning needs.
  • D. Mugar Memorial Library
    Mugar Memorial Library is the main academic library of Boston University, serving as a central hub for research and study across its disciplines.
  • E. Irwin Library
    Irwin Library is the main academic library at Butler University in Indianapolis, Indiana, supporting the university’s teaching and research needs.
  • 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_69ad8b0fbab081908f6a61567c045d8d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad986d9a248190927efc1a0c7d247f completed March 8, 2026, 3:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69b08686b0388190a214ad8a615f2da5 completed March 10, 2026, 9 p.m.
Created at: March 8, 2026, 2:56 p.m.