Triple

T7920494

Position	Surface form	Disambiguated ID	Type / Status
Subject	Department of Medicine, Johns Hopkins University	`E183931`	entity
Predicate	hasSubunit	`P747`	FINISHED
Object	Division of Endocrinology, Diabetes and Metabolism, Johns Hopkins University The Division of Endocrinology, Diabetes and Metabolism at Johns Hopkins University is a clinical and research unit specializing in hormonal disorders, diabetes care, and metabolic diseases within the institution’s Department of Medicine.	`E697027`	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 Endocrinology, Diabetes and Metabolism, Johns Hopkins University | Statement: [Department of Medicine, Johns Hopkins University, hasSubunit, Division of Endocrinology, Diabetes and Metabolism, Johns Hopkins University]

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

Target entity: Division of Endocrinology, Diabetes and Metabolism, Johns Hopkins University
Context triple: [Department of Medicine, Johns Hopkins University, hasSubunit, Division of Endocrinology, Diabetes and Metabolism, Johns Hopkins University]

A. Department of Endocrinology
The Department of Endocrinology is a clinical and research unit specializing in hormonal and metabolic disorders within the University Medical Center Göttingen.
B. Institute of Nutrition, Metabolism and Diabetes
The Institute of Nutrition, Metabolism and Diabetes is a specialized branch of Canada’s federal health research funding agency that supports research on diet, metabolic processes, and diabetes-related health issues.
C. Joslin Diabetes Center
Joslin Diabetes Center is a world-renowned medical and research institution specializing in diabetes care, education, and scientific investigation.
D. Centre for Diabetes Research
The Centre for Diabetes Research is a specialized research unit focused on studying diabetes, its causes, prevention, and treatment within the broader framework of public health.
E. National Institute of Diabetes and Digestive and Kidney Diseases
The National Institute of Diabetes and Digestive and Kidney Diseases is a U.S. government biomedical research institute that conducts and supports research on diabetes, digestive disorders, kidney diseases, and related metabolic and endocrine conditions.
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 Endocrinology, Diabetes and Metabolism, Johns Hopkins University
Triple: [Department of Medicine, Johns Hopkins University, hasSubunit, Division of Endocrinology, Diabetes and Metabolism, Johns Hopkins University]

Generated description

The Division of Endocrinology, Diabetes and Metabolism at Johns Hopkins University is a clinical and research unit specializing in hormonal disorders, diabetes care, and metabolic diseases within the institution’s Department of Medicine.

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

Target entity: Division of Endocrinology, Diabetes and Metabolism, Johns Hopkins University
Target entity description: The Division of Endocrinology, Diabetes and Metabolism at Johns Hopkins University is a clinical and research unit specializing in hormonal disorders, diabetes care, and metabolic diseases within the institution’s Department of Medicine.

A. Department of Endocrinology
The Department of Endocrinology is a clinical and research unit specializing in hormonal and metabolic disorders within the University Medical Center Göttingen.
B. Institute of Nutrition, Metabolism and Diabetes
The Institute of Nutrition, Metabolism and Diabetes is a specialized branch of Canada’s federal health research funding agency that supports research on diet, metabolic processes, and diabetes-related health issues.
C. Joslin Diabetes Center
Joslin Diabetes Center is a world-renowned medical and research institution specializing in diabetes care, education, and scientific investigation.
D. Centre for Diabetes Research
The Centre for Diabetes Research is a specialized research unit focused on studying diabetes, its causes, prevention, and treatment within the broader framework of public health.
E. National Institute of Diabetes and Digestive and Kidney Diseases
The National Institute of Diabetes and Digestive and Kidney Diseases is a U.S. government biomedical research institute that conducts and supports research on diabetes, digestive disorders, kidney diseases, and related metabolic and endocrine conditions.
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.