Triple

T26549
Position Surface form Disambiguated ID Type / Status
Subject Harvard Law School E531 entity
Predicate hasFacility P105 FINISHED
Object Caspersen Student Center E15843 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: Caspersen Student Center | Statement: [Harvard Law School, hasFacility, Caspersen Student Center]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caspersen Student Center
Context triple: [Harvard Law School, hasFacility, Caspersen Student Center]
  • A. Straus Hall
    Straus Hall is an undergraduate dormitory in Harvard Yard at Harvard University, known for housing first-year students.
  • B. Spangler Center
    Spangler Center is a central student and community hub at Harvard Business School that houses dining, study, and social spaces for MBA students.
  • C. Wasserstein Hall chosen
    Wasserstein Hall is a major academic and administrative complex at Harvard Law School that houses classrooms, offices, and student spaces.
  • D. Matthews Hall
    Matthews Hall is a historic red-brick freshman dormitory at Harvard University, located in Harvard Yard.
  • E. John A. Wilson Building
    The John A. Wilson Building is a historic government office building in Washington, D.C., that houses the city’s primary municipal and legislative 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_69a243b4ac2c8190b93c303df797b7b2 completed Feb. 28, 2026, 1:24 a.m.
NER Named-entity recognition batch_69a246776cf48190aca9855cb07e8d89 completed Feb. 28, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2b8599e2c8190a593f2c00e293f9d completed Feb. 28, 2026, 9:41 a.m.
Created at: Feb. 28, 2026, 1:34 a.m.