Triple

T20039429
Position Surface form Disambiguated ID Type / Status
Subject Mack Library E497370 entity
Predicate name P16 FINISHED
Object Mack 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: Mack Library | Statement: [Mack Library, name, Mack Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mack Library
Context triple: [Mack Library, name, Mack Library]
  • A. Mack Library chosen
    Mack Library is the main academic library serving the students and faculty of Bob Jones University in Greenville, South Carolina.
  • B. Lackman Library
    Lackman Library is a public branch of the Johnson County Library system serving local community needs with books, media, and library services.
  • C. Carmichael Library
    Carmichael Library is a public library serving the community of Carmichael, California as part of the local public library system.
  • D. Mears Library
    Mears Library is the main academic library serving the students and faculty of the University of Sioux Falls in South Dakota.
  • E. McClay Library
    McClay Library is the main academic library of Queen’s University Belfast, known for its extensive collections and modern study facilities serving students and researchers across disciplines.
  • 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_69da627278c88190babe4297a9df1236 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662e9e99c81909b7d50eac893c414 completed April 20, 2026, 5:31 p.m.
Created at: April 11, 2026, 3:36 p.m.