Triple
T28113423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Special Task Force (South African Police Service) |
E710553
|
entity |
| Predicate | lawEnforcementAgencyOf |
P67243
|
FINISHED |
| Object | South Africa |
—
|
NE NERFINISHED |
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: South Africa | Statement: [Special Task Force (South African Police Service), lawEnforcementAgencyOf, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lawEnforcementAgencyOf Context triple: [Special Task Force (South African Police Service), lawEnforcementAgencyOf, South Africa]
-
A.
lawEnforcementOrganization
Indicates that the subject is an organization whose primary role is to enforce laws and maintain public order.
-
B.
enforcementAgency
Indicates that one entity serves as the authority responsible for enforcing laws, rules, or regulations related to another entity.
-
C.
stateAgencyOf
Indicates that one entity is a governmental agency that operates under the authority or jurisdiction of a particular state.
-
D.
policeBureau
chosen
Indicates that an entity functions as or is associated with a police bureau or police department.
-
E.
lawEnforcementLabel
Indicates that an entity has been designated, tagged, or classified by a law enforcement authority for monitoring, identification, or investigative purposes.
- 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_69ef9b72f63081909dfbc2c1ddae86c6 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f640ca4480819089a6b9fd78c45ab2 |
completed | May 2, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9:12 p.m.