Triple

T5982355
Position Surface form Disambiguated ID Type / Status
Subject al-Qaida in the Land of the Two Rivers E133147 entity
Predicate usedPropagandaMedium P3163 FINISHED
Object online videos 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: online videos | Statement: [al-Qaida in the Land of the Two Rivers, usedPropagandaMedium, online videos]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usedPropagandaMedium
Context triple: [al-Qaida in the Land of the Two Rivers, usedPropagandaMedium, online videos]
  • A. usedInPropaganda chosen
    Indicates that something is employed as a tool or element within propaganda efforts to influence opinions or behavior.
  • B. usesPropagandaExtensively
    Indicates that an entity systematically employs propaganda as a primary or pervasive tool to influence opinions, beliefs, or behavior.
  • C. typeOfPropaganda
    Indicates that one entity is a specific kind or category of propaganda employed or represented by another entity.
  • D. usedMedium
    Indicates that an action or communication was carried out through a particular medium or channel.
  • E. languageOfPropaganda
    Indicates that a particular language is used as the medium or vehicle for disseminating propaganda.
  • 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_69c0086f45e8819098f73dd16d45ec9d completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04a6921b081908a6f6323d5c7a062 completed March 22, 2026, 8 p.m.
PD Predicate disambiguation batch_69c049de98648190962b14fd341c93da completed March 22, 2026, 7:58 p.m.
Created at: March 22, 2026, 4:04 p.m.