Triple
T665374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J. B. M. Hertzog |
E12848
|
entity |
| Predicate | termInOffice |
P17403
|
FINISHED |
| Object | fifth Prime Minister of South Africa |
—
|
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: fifth Prime Minister of South Africa | Statement: [J. B. M. Hertzog, termInOffice, fifth Prime Minister of South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termInOffice Context triple: [J. B. M. Hertzog, termInOffice, fifth Prime Minister of South Africa]
-
A.
termLength
Indicates the duration or period of time for which an agreement, position, or condition remains in effect.
-
B.
presidentialTerm
Indicates the period of time during which an individual officially serves as president of a country or organization.
-
C.
parliamentaryTerm
Indicates the specific legislative session or fixed period of time during which a parliament is formally in office and exercises its authority.
-
D.
setsTermOfOfficeFor
Indicates that one entity establishes or defines the duration and conditions of the term of office for another entity.
-
E.
legislativeTermNumber
Indicates the ordinal number assigned to a specific legislative term within a sequence of legislative periods.
- 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_69a493355dec819098d4244b2fa34885 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49fd4f4988190a0973ceb7329b4c9 |
completed | March 1, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69a49d16cff881908c8d2c3fe4d1d6fb |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49df19c9481909cc9bc33ed7f011b |
completed | March 1, 2026, 8:13 p.m. |
Created at: March 1, 2026, 7:36 p.m.