Triple
T18914569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Discovery Park (Purdue University) |
E462691
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Regenstrief Center for Healthcare Engineering |
—
|
NE NERFINISHED |
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: Regenstrief Center for Healthcare Engineering | Statement: [Discovery Park (Purdue University), hasPart, Regenstrief Center for Healthcare Engineering]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Regenstrief Center for Healthcare Engineering Context triple: [Discovery Park (Purdue University), hasPart, Regenstrief Center for Healthcare Engineering]
-
A.
Regenstrief Center for Healthcare Engineering at Purdue University
chosen
The Regenstrief Center for Healthcare Engineering at Purdue University is an interdisciplinary research center that applies engineering, data science, and systems thinking to improve healthcare delivery, quality, and efficiency.
-
B.
Regenstrief Institute
Regenstrief Institute is a medical research organization known for its pioneering work in health informatics and the development of widely used clinical data standards.
-
C.
Regenstrief Medical Record System
The Regenstrief Medical Record System is an early, pioneering electronic medical record platform that helped shape modern health informatics and clinical data management practices.
-
D.
Stanford Center for Biomedical Informatics Research
The Stanford Center for Biomedical Informatics Research is a leading Stanford University hub for developing computational methods and tools to advance biomedical data analysis, clinical decision support, and translational medicine.
-
E.
National Institute for Health Innovation
The National Institute for Health Innovation is a research centre focused on developing and evaluating innovative strategies to improve public health and healthcare outcomes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c625b4fc8190a9dda6e76afa573e |
completed | April 20, 2026, 6:22 a.m. |
Created at: April 10, 2026, 11:58 a.m.