Triple
T30846526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wilayat al-Yaman |
E785647
|
entity |
| Predicate | usesRecruitmentMethod |
P138499
|
FINISHED |
| Object | online propaganda |
—
|
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 propaganda | Statement: [Wilayat al-Yaman, usesRecruitmentMethod, online propaganda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesRecruitmentMethod Context triple: [Wilayat al-Yaman, usesRecruitmentMethod, online propaganda]
-
A.
recruitmentMethods
chosen
Indicates the ways or strategies used to attract, source, and enlist individuals for a role, program, or organization.
-
B.
usedForcedRecruitment
Indicates that an entity compelled others to join or serve, typically through coercion, threats, or violence, rather than through voluntary enlistment.
-
C.
hasDraftOrRecruitmentMethod
Indicates that there exists a specific draft system or recruitment method used to select or acquire participants or members.
-
D.
employedMethod
Indicates that a particular method, technique, or procedure was used to carry out an action or achieve a result.
-
E.
vacancyFillingMethod
Indicates the method or process by which a vacant position, seat, or role is filled.
- 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_69f224b850848190a4af4ccf8ddadcdf |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 29, 2026, 8:46 p.m.