Triple
T1989238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General Directorate of Police Hospitals |
E43212
|
entity |
| Predicate | typeOfPatients |
P19115
|
FINISHED |
| Object | law enforcement personnel |
—
|
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: law enforcement personnel | Statement: [General Directorate of Police Hospitals, typeOfPatients, law enforcement personnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPatients Context triple: [General Directorate of Police Hospitals, typeOfPatients, law enforcement personnel]
-
A.
diseaseType
Indicates that one entity is classified as a specific type or category of disease in relation to another entity.
-
B.
healthcareType
Indicates the category or kind of healthcare service, system, or coverage associated with an entity.
-
C.
hasPatient
Indicates that an action, event, or process involves a specific entity as the one undergoing or receiving its effects (the patient).
-
D.
categoryOfPeopleServed
chosen
Indicates the type or group of people that are the primary recipients or beneficiaries of a service or activity.
-
E.
typeOfCasesHandled
Indicates the categories or kinds of cases that an entity (such as a person, organization, or system) is responsible for managing or processing.
- 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_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:37 p.m.