Triple
T31994370
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faculty of Medicine, University of Gezira |
E816954
|
entity |
| Predicate | countryHealthSystemContext |
P15635
|
FINISHED |
| Object | Sudan health system |
—
|
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: Sudan health system | Statement: [Faculty of Medicine, University of Gezira, countryHealthSystemContext, Sudan health system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryHealthSystemContext Context triple: [Faculty of Medicine, University of Gezira, countryHealthSystemContext, Sudan health system]
-
A.
healthSystem
chosen
Indicates a relationship where an entity functions as, belongs to, or is managed within a particular health care system or network.
-
B.
healthSystemLevel
Indicates the level or tier within a health system at which a given action, service, or relationship occurs (e.g., local, regional, national).
-
C.
shareHealthSystem
Indicates that two entities are served by, or belong to, the same healthcare system or network.
-
D.
hasHealthcareInfrastructure
Indicates that an entity possesses facilities, systems, and resources necessary to deliver healthcare services.
-
E.
designatedAsFlagshipHospitalFor
Indicates that one hospital has been officially selected or recognized as the primary or leading flagship institution for another entity (such as a health system, region, or organization).
- 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_69f348f8002081909a3588758ba94afb |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a001cc0ff588190bb7c8a6fd427d02b |
completed | May 10, 2026, 5:50 a.m. |
| PD | Predicate disambiguation | batch_6a001b3ea18c8190aeda7a32b2697490 |
completed | May 10, 2026, 5:44 a.m. |
Created at: May 1, 2026, 12:13 a.m.