Triple
T6064055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faculty of Medicine Heidelberg |
E135109
|
entity |
| Predicate | hasClinicalTrainingSitesIn |
P465
|
FINISHED |
| Object | Heidelberg University Hospital |
E569664
|
NE FINISHED |
How this triple was built (3 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: Heidelberg University Hospital | Statement: [Faculty of Medicine Heidelberg, hasClinicalTrainingSitesIn, Heidelberg University Hospital]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heidelberg University Hospital Context triple: [Faculty of Medicine Heidelberg, hasClinicalTrainingSitesIn, Heidelberg University Hospital]
-
A.
Heidelberg University Hospital
chosen
Heidelberg University Hospital is a major German academic medical center in Heidelberg, renowned for its advanced clinical care, biomedical research, and close integration with Heidelberg University.
-
B.
University Hospital of Cologne
The University Hospital of Cologne is a major German teaching and research hospital providing comprehensive medical care in close collaboration with the University of Cologne.
-
C.
Faculty of Medicine Heidelberg
The Faculty of Medicine Heidelberg is the medical school of Heidelberg University, renowned for its research-intensive programs and clinical training in one of Germany’s leading academic medical centers.
-
D.
Erlangen University Hospital
Erlangen University Hospital is a major teaching and research hospital in Erlangen, Germany, closely integrated with the University of Erlangen-Nuremberg’s medical faculty.
-
E.
University Hospital Bonn
University Hospital Bonn is a major academic medical center in Bonn, Germany, providing advanced clinical care, medical research, and teaching in partnership with the University of Bonn.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasClinicalTrainingSitesIn Context triple: [Faculty of Medicine Heidelberg, hasClinicalTrainingSitesIn, Heidelberg University Hospital]
-
A.
servesAsTeachingSiteFor
Indicates that one entity functions as a location or institution where teaching, training, or educational activities are conducted for another entity.
-
B.
isTeachingHospitalFor
chosen
Indicates that one institution serves as a clinical training site or educational facility for another, typically a medical school or health education program.
-
C.
hasInstitutions
Indicates that one entity possesses, contains, or is associated with one or more institutions.
-
D.
servesAsPrimaryTeachingHospitalFor
Indicates that one institution functions as the main clinical training and teaching site for another institution, typically a medical school or academic program.
-
E.
establishedAsClinicalSchool
Indicates that an institution or facility has been formally designated and recognized as a clinical school for education and training purposes.
- F. None of above.
Provenance (4 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_69c00878d06881909ee78e88913bf890 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05723c91c819090b4d4672e72f9f3 |
completed | March 22, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1414ea324819087dc9267938efb5c |
completed | March 23, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69c049f031408190b08b2766237c5dd0 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:10 p.m.