Triple
T4004934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Union |
E89502
|
entity |
| Predicate | regimeTypeSupported |
P32911
|
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: [National Union, regimeTypeSupported, authoritarian regime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regimeTypeSupported Context triple: [National Union, regimeTypeSupported, authoritarian regime]
-
A.
regimeType
Indicates the form or system of governance under which an entity (such as a state or organization) is ruled or administered.
-
B.
supportsType
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
C.
supportedRegime
chosen
Indicates that an entity provided assistance, endorsement, or backing to a particular political regime or government in power.
-
D.
supportsProgramType
Indicates that one entity is capable of handling, offering, or being compatible with a specified type of program.
-
E.
supportsPatternType
Indicates that one entity is compatible with, or capable of handling, a specified pattern type.
- 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_69aed9585e788190bec2d39deba3750f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa8579288190940487ad07e38de0 |
completed | March 9, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69aef8f89f2881909b0965419d15d46c |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:34 p.m.