Triple

T8061
Position Surface form Disambiguated ID Type / Status
Subject School of Medicine, Duke University E159 entity
Predicate hasAcademicDepartment P589 FINISHED
Object Department of Radiology, Duke University
The Department of Radiology at Duke University is a leading academic and clinical radiology center known for advanced imaging research, innovative diagnostic and interventional services, and comprehensive resident and fellowship training.
E3813 NE FINISHED

How this triple was built (4 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: Department of Radiology, Duke University | Statement: [School of Medicine, Duke University, hasAcademicDepartment, Department of Radiology, Duke University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Department of Radiology, Duke University
Context triple: [School of Medicine, Duke University, hasAcademicDepartment, Department of Radiology, Duke University]
  • A. Department of Pathology, Duke University
    The Department of Pathology at Duke University is an academic and clinical department specializing in the study, diagnosis, and research of disease within the Duke University School of Medicine.
  • B. Department of Surgery, Duke University
    The Department of Surgery at Duke University is a major academic surgical department known for its clinical excellence, surgical innovation, and research and training programs within Duke’s medical school.
  • C. School of Medicine, Duke University
    The School of Medicine at Duke University is a leading U.S. medical school renowned for its research-intensive programs, innovative medical education, and strong clinical partnerships.
  • D. Department of Neurosurgery, Duke University
    The Department of Neurosurgery at Duke University is a leading academic and clinical center specializing in advanced neurosurgical care, research, and education within the Duke University School of Medicine.
  • E. Department of Pediatrics, Duke University
    The Department of Pediatrics at Duke University is a major academic and clinical center focused on advancing children's health through pediatric education, research, and patient care within Duke's medical school.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Department of Radiology, Duke University
Triple: [School of Medicine, Duke University, hasAcademicDepartment, Department of Radiology, Duke University]
Generated description
The Department of Radiology at Duke University is a leading academic and clinical radiology center known for advanced imaging research, innovative diagnostic and interventional services, and comprehensive resident and fellowship training.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Department of Radiology, Duke University
Target entity description: The Department of Radiology at Duke University is a leading academic and clinical radiology center known for advanced imaging research, innovative diagnostic and interventional services, and comprehensive resident and fellowship training.
  • A. Department of Pathology, Duke University
    The Department of Pathology at Duke University is an academic and clinical department specializing in the study, diagnosis, and research of disease within the Duke University School of Medicine.
  • B. Department of Surgery, Duke University
    The Department of Surgery at Duke University is a major academic surgical department known for its clinical excellence, surgical innovation, and research and training programs within Duke’s medical school.
  • C. School of Medicine, Duke University
    The School of Medicine at Duke University is a leading U.S. medical school renowned for its research-intensive programs, innovative medical education, and strong clinical partnerships.
  • D. Department of Neurosurgery, Duke University
    The Department of Neurosurgery at Duke University is a leading academic and clinical center specializing in advanced neurosurgical care, research, and education within the Duke University School of Medicine.
  • E. Department of Pediatrics, Duke University
    The Department of Pediatrics at Duke University is a major academic and clinical center focused on advancing children's health through pediatric education, research, and patient care within Duke's medical school.
  • F. None of above. chosen

Provenance (5 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_69a23bb612708190b09f25385e4b63d1 completed Feb. 28, 2026, 12:49 a.m.
NER Named-entity recognition batch_69a24659cfe0819088c2e8a61c2274f3 completed Feb. 28, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69a24e52b304819094ffde051ec9bde3 completed Feb. 28, 2026, 2:09 a.m.
NEDg Description generation batch_69a24ede3374819089e7fae28c6c9d63 completed Feb. 28, 2026, 2:11 a.m.
NED2 Entity disambiguation (via description) batch_69a24fc8a2a881909e5ae2e03757fbec completed Feb. 28, 2026, 2:15 a.m.
Created at: Feb. 28, 2026, 12:54 a.m.