Triple

T13115561
Position Surface form Disambiguated ID Type / Status
Subject Tydings Hall E311082 entity
Predicate near P350 FINISHED
Object Shoemaker Building E311086 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: Shoemaker Building | Statement: [Tydings Hall, near, Shoemaker Building]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shoemaker Building
Context triple: [Tydings Hall, near, Shoemaker Building]
  • A. Shoemaker Building chosen
    Shoemaker Building is an academic and administrative facility located on the University of Maryland’s McKeldin Mall in College Park.
  • B. Morton Building
    Morton Building is a historic African American–owned vaudeville theater and cultural landmark located in Athens, Georgia.
  • C. Buckwalter Building
    The Buckwalter Building is a historic commercial structure located in downtown West Chester, Pennsylvania, recognized for its architectural and local heritage significance.
  • D. Sawyer Building
    The Sawyer Building is an academic facility of Suffolk University in Boston that houses classrooms, offices, and various university services.
  • E. Waterman Building
    The Waterman Building is a central administrative and academic facility on the campus of the University of Vermont in Burlington.
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98180b6ac8190ae5a1f7c1480bd54 completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e28105c481908781775ba489c296 completed May 3, 2026, 5:52 a.m.
Created at: April 9, 2026, 9:06 p.m.