Triple

T16157694
Position Surface form Disambiguated ID Type / Status
Subject Burnside Hall E392087 entity
Predicate near P350 FINISHED
Object Leacock Building E395057 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: Leacock Building | Statement: [Burnside Hall, near, Leacock Building]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leacock Building
Context triple: [Burnside Hall, near, Leacock Building]
  • A. Leacock Building chosen
    The Leacock Building is a major academic and classroom complex at McGill University’s downtown Montreal campus, housing numerous lecture halls, offices, and social science departments.
  • B. Johnson Building
    The Johnson Building is a modernist wing of the Boston Public Library’s Copley Square main branch, known for housing its contemporary collections and public services.
  • C. Rockefeller Building
    The Rockefeller Building is a historic University College London structure in Bloomsbury that houses academic departments and museums, including the Grant Museum of Zoology.
  • D. Eastman Building
    The Eastman Building is a historic structure in Brussels that now serves as the home of the House of European History museum.
  • E. Hylan Building
    The Hylan Building is an academic facility on the University of Rochester’s River Campus that primarily houses mathematics and computer science departments, classrooms, and offices.
  • 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21e5b57a48190b6fe21f1c63e1ba3 completed April 17, 2026, 11:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7b05a588190a44d1c922195a87b completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:01 a.m.