Triple
T13962766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sostiene Pereira |
E335837
|
entity |
| Predicate | settingRegimeType |
P49415
|
FINISHED |
| Object | authoritarian regime |
—
|
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: authoritarian regime | Statement: [Sostiene Pereira, settingRegimeType, authoritarian regime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: settingRegimeType Context triple: [Sostiene Pereira, settingRegimeType, authoritarian regime]
-
A.
regimeType
chosen
Indicates the form or system of governance under which an entity (such as a state or organization) is ruled or administered.
-
B.
usedByRegimeType
Indicates that something (such as a method, policy, or tool) is employed or implemented by a particular type of political regime.
-
C.
modeType
Indicates the specific manner, method, or operational mode in which an action, process, or system is carried out or functions.
-
D.
settingControlled
Indicates that one entity regulates, adjusts, or determines the configuration or parameters of another entity.
-
E.
settingLocationType
Indicates the type or category of location in which an event, action, or situation takes place.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e7c73d48190b8e02971b5a8ed5f |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69de05a3ccf88190b45c742db483fa08 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:18 p.m.