Triple
T20363808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The First Affiliated Hospital of China Medical University |
E496854
|
entity |
| Predicate | hospitalLevel |
P139853
|
FINISHED |
| Object | tertiary |
—
|
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: tertiary | Statement: [The First Affiliated Hospital of China Medical University, hospitalLevel, tertiary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hospitalLevel Context triple: [The First Affiliated Hospital of China Medical University, hospitalLevel, tertiary]
-
A.
healthSystemLevel
Indicates the level or tier within a health system at which a given action, service, or relationship occurs (e.g., local, regional, national).
-
B.
majorHospital
Indicates that a hospital holds a primary or leading status within a healthcare system or region, typically due to its size, capacity, or range of services.
-
C.
hospitalLocation
Indicates the geographic place or address where a hospital is situated.
-
D.
hasHospitalType
Indicates that a hospital is classified as belonging to a specific type or category (e.g., general, specialized, teaching).
-
E.
containsHospital
Indicates that one entity includes or encompasses a hospital within its boundaries or composition.
- F. None of above. chosen
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_69e0b4a4f9b081908a5a021919c21ccb |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6786fd0088190908187ab642344cc |
completed | April 20, 2026, 7:03 p.m. |
| PD | Predicate disambiguation | batch_69e57648be3c81908256838228cabf5c |
completed | April 20, 2026, 12:41 a.m. |
| PDg | Predicate description generation | batch_69e58d7481508190a87c8b88f9df9879 |
completed | April 20, 2026, 2:20 a.m. |
Created at: April 16, 2026, 11:26 a.m.