Triple
T27760871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Democratic Party of Equatorial Guinea |
E701464
|
entity |
| Predicate | systemCharacterization |
P163838
|
FINISHED |
| Object | de facto one-party state |
—
|
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: de facto one-party state | Statement: [Democratic Party of Equatorial Guinea, systemCharacterization, de facto one-party state]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: systemCharacterization Context triple: [Democratic Party of Equatorial Guinea, systemCharacterization, de facto one-party state]
-
A.
systemCharacteristics
Indicates the defining properties, behaviors, and constraints that characterize how a system operates or is configured.
-
B.
sourceCharacterization
Indicates that one entity describes, explains, or characterizes the origin, provenance, or source of another entity.
-
C.
systemNotableCharacteristic
chosen
Indicates that a system possesses a particular distinguishing feature or attribute that is especially noteworthy or significant.
-
D.
theoryCharacterization
Indicates that one entity provides a defining description, formulation, or account of a theory associated with another entity.
-
E.
standardCharacterization
Indicates that something is described, defined, or represented according to an accepted or commonly used standard.
- 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_69ef6a5193808190816eb7d0020b2d87 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 27, 2026, 4:26 p.m.