Triple

T7920498

Position	Surface form	Disambiguated ID	Type / Status
Subject	Department of Medicine, Johns Hopkins University	`E183931`	entity
Predicate	hasSubunit	`P747`	FINISHED
Object	Division of Oncology, Johns Hopkins University The Division of Oncology at Johns Hopkins University is a major academic and clinical unit specializing in cancer research, treatment, and education within the institution’s Department of Medicine.	`E697031`	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: Division of Oncology, Johns Hopkins University | Statement: [Department of Medicine, Johns Hopkins University, hasSubunit, Division of Oncology, Johns Hopkins University]

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Division of Oncology, Johns Hopkins University
Context triple: [Department of Medicine, Johns Hopkins University, hasSubunit, Division of Oncology, Johns Hopkins University]

A. Division of Cancer Treatment and Diagnosis
The Division of Cancer Treatment and Diagnosis is a branch of the National Cancer Institute that supports the development, evaluation, and clinical testing of new cancer therapies and diagnostic tools.
B. Department of Oncology
The Department of Oncology at the University Medical Center Göttingen is a clinical and research unit specializing in the diagnosis, treatment, and study of cancer.
C. Department of Oncology
The Department of Oncology at Johns Hopkins School of Medicine is a leading academic and clinical center focused on cancer research, treatment, and education.
D. Department of Oncology
The Department of Oncology is an academic and clinical unit at McGill University’s Faculty of Medicine and Health Sciences dedicated to cancer research, education, and patient care.
E. Department of Oncology
The Department of Oncology at University Hospital Zurich is a leading medical and research center specializing in the diagnosis, treatment, and study of cancer.
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: Division of Oncology, Johns Hopkins University
Triple: [Department of Medicine, Johns Hopkins University, hasSubunit, Division of Oncology, Johns Hopkins University]

Generated description

The Division of Oncology at Johns Hopkins University is a major academic and clinical unit specializing in cancer research, treatment, and education within the institution’s Department of Medicine.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Division of Oncology, Johns Hopkins University
Target entity description: The Division of Oncology at Johns Hopkins University is a major academic and clinical unit specializing in cancer research, treatment, and education within the institution’s Department of Medicine.

A. Division of Cancer Treatment and Diagnosis
The Division of Cancer Treatment and Diagnosis is a branch of the National Cancer Institute that supports the development, evaluation, and clinical testing of new cancer therapies and diagnostic tools.
B. Department of Oncology
The Department of Oncology at the University Medical Center Göttingen is a clinical and research unit specializing in the diagnosis, treatment, and study of cancer.
C. Department of Oncology
The Department of Oncology at Charité – Universitätsmedizin Berlin is a leading clinical and research center specializing in the diagnosis, treatment, and study of cancer.
D. Department of Oncology
The Department of Oncology at Johns Hopkins School of Medicine is a leading academic and clinical center focused on cancer research, treatment, and education.
E. Department of Oncology
The Department of Oncology is an academic and clinical unit at McGill University’s Faculty of Medicine and Health Sciences dedicated to cancer research, education, and patient care.
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_69ca828efbe48190bd48482650182e79`	completed	March 30, 2026, 2:02 p.m.
NER	Named-entity recognition	`batch_69cb3a9360f881908ca2433d0623315b`	completed	March 31, 2026, 3:08 a.m.
NED1	Entity disambiguation (via context triple)	`batch_69cb5beea7988190972f7d02881d98f6`	completed	March 31, 2026, 5:30 a.m.
NEDg	Description generation	`batch_69cb5f222c808190b9ef39896f149278`	completed	March 31, 2026, 5:44 a.m.
NED2	Entity disambiguation (via description)	`batch_69cb76bb9a308190a9d7b34838d696db`	completed	March 31, 2026, 7:24 a.m.

Created at: March 30, 2026, 5:06 p.m.