Triple
T1412629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Reserve Bank |
E31837
|
entity |
| Predicate | employerInIndustry |
P6744
|
FINISHED |
| Object | central banking industry |
—
|
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: central banking industry | Statement: [South African Reserve Bank, employerInIndustry, central banking industry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employerInIndustry Context triple: [South African Reserve Bank, employerInIndustry, central banking industry]
-
A.
employerType
Indicates the classification or category of an employer in relation to the entity (e.g., public, private, nonprofit, self-employed).
-
B.
collegeEmployer
Indicates that a college or university is the employing institution of a given person or organization.
-
C.
industryOfUnderlyingCompany
chosen
Indicates the industry sector in which the underlying company associated with this entity operates.
-
D.
positionInIndustry
Indicates the role, rank, or standing that an entity holds within a particular industry or sector.
-
E.
employmentType
Indicates the specific kind or category of employment relationship that exists between an individual and an employer (e.g., full-time, part-time, contract).
- 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_69a49919a994819086528951bc224775 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c3e3383c81909acb9c6c1c3b817a |
completed | March 1, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69a4bf048b648190ab77d9b45cb4855f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.