Triple
T10652693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African politics |
E251009
|
entity |
| Predicate | transitionMechanism |
P3705
|
FINISHED |
| Object | negotiated settlement |
—
|
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: negotiated settlement | Statement: [South African politics, transitionMechanism, negotiated settlement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transitionMechanism Context triple: [South African politics, transitionMechanism, negotiated settlement]
-
A.
transitionMechanismUsedWith
chosen
Indicates that a particular transition or change from one state to another is carried out using a specified mechanism or method.
-
B.
transition
Indicates a change of state or condition from one form, phase, or situation to another.
-
C.
transitionProgram
Indicates a relationship where one entity serves as a program or structured process that facilitates another entity’s transition from one state, phase, or condition to another.
-
D.
transitionCharacteristic
Indicates a relationship where an entity is characterized by how it changes state or condition over time or between phases.
-
E.
transitionTo
Indicates a change in state, condition, or phase from one defined status to another.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dff78ec88190a4d1863fe87245f6 |
completed | April 8, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69d6dd8753108190b799ffa0c760526e |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 9:06 p.m.