Triple
T1079005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | President of South Africa |
E23902
|
entity |
| Predicate | cannotHoldSimultaneously |
P23670
|
FINISHED |
| Object | provincial premiership |
—
|
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: provincial premiership | Statement: [President of South Africa, cannotHoldSimultaneously, provincial premiership]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cannotHoldSimultaneously Context triple: [President of South Africa, cannotHoldSimultaneously, provincial premiership]
-
A.
mayBeHeldConcurrentlyWith
Indicates that one event, state, or condition is allowed to occur or be in effect at the same time as another without conflict or violation of constraints.
-
B.
canOperateInMultiple
Indicates that an entity is capable of functioning or being used across more than one context, environment, or mode.
-
C.
canHold
Indicates that one entity has the capacity or ability to contain, support, or carry another entity.
-
D.
mayHold
Indicates that one entity is permitted or allowed to possess, contain, or maintain another entity.
-
E.
notHeldDuring
Indicates that a specified condition, event, or relationship does not occur or is not in effect throughout a given time interval or temporal context.
- 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_69a493f1ddf48190a99d54b00e99f8ce |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b943b41481909b24050ca7e78971 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b73d9f08819093668104f129840e |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b80f0fb08190a19a50e38ae8f16c |
completed | March 1, 2026, 10:05 p.m. |
Created at: March 1, 2026, 7:42 p.m.