Triple
T5173169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gonzalo Queipo de Llano |
E116732
|
entity |
| Predicate | propagandaType |
P20122
|
FINISHED |
| Object | incendiary speeches |
—
|
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: incendiary speeches | Statement: [Gonzalo Queipo de Llano, propagandaType, incendiary speeches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: propagandaType Context triple: [Gonzalo Queipo de Llano, propagandaType, incendiary speeches]
-
A.
typeOfPropaganda
chosen
Indicates that one entity is a specific kind or category of propaganda employed or represented by another entity.
-
B.
propagandaOrgan
Indicates that one entity functions as a propaganda-producing or propaganda-disseminating organ on behalf of another entity.
-
C.
languageOfPropaganda
Indicates that a particular language is used as the medium or vehicle for disseminating propaganda.
-
D.
usedInPropaganda
Indicates that something is employed as a tool or element within propaganda efforts to influence opinions or behavior.
-
E.
hasPropagandist
Indicates that one entity serves as a propagandist who creates or disseminates propaganda on behalf of another entity.
- 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_69bd445ff97c81909a2615cc56235470 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd796f7c308190a721e33aabd499ac |
completed | March 20, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69bd77b529948190b86671ebe43f4734 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:45 p.m.