Triple
T2121956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pashto media |
E43944
|
entity |
| Predicate | servesDiaspora |
P30816
|
FINISHED |
| Object | global Pashtun diaspora |
—
|
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: global Pashtun diaspora | Statement: [Pashto media, servesDiaspora, global Pashtun diaspora]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesDiaspora Context triple: [Pashto media, servesDiaspora, global Pashtun diaspora]
-
A.
isUsedByDiaspora
chosen
Indicates that something is utilized, practiced, or maintained by members of a diaspora community.
-
B.
hasDiaspora
Indicates that a group, community, or population has members who have dispersed or settled outside their original homeland or region.
-
C.
diasporaType
Indicates the specific kind or category of diaspora relationship that exists between a group and its place of origin.
-
D.
servesUsers
Indicates that an entity provides services, functionality, or benefits to one or more users.
-
E.
servesOn
Indicates that one entity performs duties, functions, or holds a role as a member within another entity, such as a group, body, or organization.
- 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_69a88717cfe48190b7ecdd68c824848a |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb51e8088190a1aeafee4e8dff63 |
completed | March 7, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_69abb7bd86cc8190938ef06c1ed6d969 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:44 p.m.