Triple
T38505063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vihiga District |
E921741
|
entity |
| Predicate | predominantSubgroup |
P21204
|
FINISHED |
| Object | Maragoli |
—
|
NE NERFINISHED |
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: Maragoli | Statement: [Vihiga District, predominantSubgroup, Maragoli]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predominantSubgroup Context triple: [Vihiga District, predominantSubgroup, Maragoli]
-
A.
demographicMajority
chosen
Indicates that one group constitutes more than half of the population within a specified context or area.
-
B.
majorityType
Indicates that one type or category constitutes more than half of the instances within a given set or context.
-
C.
dominantCommunity
Indicates that one community holds a prevailing or controlling influence, status, or presence over others within a given context.
-
D.
dominantCluster
Indicates that one cluster in a set is the most influential or representative group relative to the others, often based on size, centrality, or impact.
-
E.
dominantComposition
Indicates that one entity is the primary or prevailing component, material, or element that makes up or characterizes 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_69f76ea3c5448190aa7002fc1ba3f874 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.