Triple

T3695712
Position Surface form Disambiguated ID Type / Status
Subject School of Law E78452 entity
Predicate shortName P43 FINISHED
Object BU Law E81832 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: BU Law | Statement: [School of Law, shortName, BU Law]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BU Law
Context triple: [School of Law, shortName, BU Law]
  • A. SUNY Buffalo Law School
    SUNY Buffalo Law School is the law school of the University at Buffalo, a public research university in New York, known for its strong clinical programs and focus on practical legal training.
  • B. Boston University School of Law chosen
    Boston University School of Law is a prestigious private law school in Boston, Massachusetts, known for its strong academic programs and influential alumni.
  • C. Maurer School of Law
    Maurer School of Law is the law school of Indiana University Bloomington, known for its strong programs in constitutional, international, and intellectual property law.
  • D. Beasley School of Law
    Beasley School of Law is the law school of Temple University in Philadelphia, known for its strong trial advocacy program and practical, skills-focused legal education.
  • E. York Law School
    York Law School is the law faculty of the University of York, offering innovative legal education and research with a strong focus on problem-based learning and interdisciplinary study.
  • 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_69ad85e3b1888190abc983e06968696d completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc50f9ad88190a926042fa73d65dc completed March 8, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c3d4821081909ccd1b5789eb761e completed March 14, 2026, 2:11 a.m.
Created at: March 8, 2026, 3:26 p.m.