Triple
T1604683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ga language |
E34473
|
entity |
| Predicate | hasDigitalUse |
P1446
|
FINISHED |
| Object | social media in Ghana |
—
|
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: social media in Ghana | Statement: [Ga language, hasDigitalUse, social media in Ghana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDigitalUse Context triple: [Ga language, hasDigitalUse, social media in Ghana]
-
A.
hasDigitalService
Indicates that an entity provides, offers, or is associated with a service delivered through digital or online means.
-
B.
hasDigitalAccess
Indicates that an entity has the ability or permission to use or access digital resources, services, or information.
-
C.
hasDigitalForm
Indicates that something exists or is available in a digital or electronic format.
-
D.
hasDigitalEncoding
Indicates that one entity is represented, stored, or expressed using a specific digital code or encoding scheme provided by another entity.
-
E.
usedInDigitalCommunication
chosen
Indicates that something is employed as a medium, tool, or element within digital or electronic communication processes.
- 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_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93fa6926081908bc78d15c0be3185 |
completed | March 5, 2026, 8:32 a.m. |
| PD | Predicate disambiguation | batch_69a907c35f848190a2428c52e81d013e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.