Triple
T38505242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luo community |
E921745
|
entity |
| Predicate | notableKenyanSubgroup |
P104422
|
FINISHED |
| Object | Kisumu Luo |
E43852
|
NE 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: Kisumu Luo | Statement: [Luo community, notableKenyanSubgroup, Kisumu Luo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableKenyanSubgroup Context triple: [Luo community, notableKenyanSubgroup, Kisumu Luo]
-
A.
notableSubgroup
Indicates that one group forms a particularly significant or noteworthy subset within a larger group.
-
B.
majorAreasKenya
Indicates that the related entities represent the principal geographic or administrative regions within Kenya.
-
C.
hasNotableSubtribe
chosen
Indicates that an entity (typically a larger tribal or ethnic group) includes a particular subtribe that is especially recognized or notable.
-
D.
isBantuGroupOf
Indicates that one entity is a subgroup, member group, or constituent group within a larger Bantu group represented by the other entity.
-
E.
notableChildrenGroup
Indicates that an entity has a group of children who are notable or significant in some recognized way.
- F. None of above.
Provenance (4 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_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41ea825b2c8190a794e5184fd29f7f |
completed | June 29, 2026, 3:46 a.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.