Triple
T9225456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Islamic State – Yemen Province |
E221670
|
entity |
| Predicate | usesPropagandaLanguage |
P50927
|
FINISHED |
| Object | Arabic |
—
|
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: Arabic | Statement: [Islamic State – Yemen Province, usesPropagandaLanguage, Arabic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesPropagandaLanguage Context triple: [Islamic State – Yemen Province, usesPropagandaLanguage, Arabic]
-
A.
usesPropagandaExtensively
Indicates that an entity systematically employs propaganda as a primary or pervasive tool to influence opinions, beliefs, or behavior.
-
B.
languageOfPropaganda
chosen
Indicates that a particular language is used as the medium or vehicle for disseminating propaganda.
-
C.
usedInPropaganda
Indicates that something is employed as a tool or element within propaganda efforts to influence opinions or behavior.
-
D.
hasPropagandaPurpose
Indicates that something is intended or used to influence opinions or behavior in a biased or manipulative way for propaganda purposes.
-
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_69ca83ec8db08190a9110df8232885d2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda9dbd1481909f35a4bee8e0b450 |
completed | April 1, 2026, 8:43 a.m. |
| PD | Predicate disambiguation | batch_69cc7a3daeb481908b0abde3fbc1f1f0 |
completed | April 1, 2026, 1:51 a.m. |
Created at: March 30, 2026, 7:28 p.m.