Triple
T2593206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karolinska University Hospital |
E58170
|
entity |
| Predicate | hasTypeOfCare |
P7500
|
FINISHED |
| Object | inpatient care |
—
|
LITERAL FINISHED |
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: inpatient care | Statement: [Karolinska University Hospital, hasTypeOfCare, inpatient care]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfCare Context triple: [Karolinska University Hospital, hasTypeOfCare, inpatient care]
-
A.
healthcareType
chosen
Indicates the category or kind of healthcare service, system, or coverage associated with an entity.
-
B.
hasHospitalType
Indicates that a hospital is classified as belonging to a specific type or category (e.g., general, specialized, teaching).
-
C.
hasFacilityType
Indicates that an entity possesses or is associated with a specific type or category of facility.
-
D.
requiresCare
Indicates that one entity depends on another to provide care, attention, or maintenance for its proper functioning or well-being.
-
E.
providesCareSetting
Indicates that one entity serves as the care environment or setting in which another entity receives or delivers care.
- F. None of above.
Provenance (3 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_69ab4ac019c8819094add11c46706e32 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd426e2d4819081a07920b4d2a1cc |
completed | March 7, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69abd0d344988190a18dd93b13e002e6 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:49 p.m.