Triple
T10020993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speaker of the National Assembly of Kenya |
E200607
|
entity |
| Predicate | legislativeHouseLevel |
P41611
|
FINISHED |
| Object | lower house |
—
|
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: lower house | Statement: [Speaker of the National Assembly of Kenya, legislativeHouseLevel, lower house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legislativeHouseLevel Context triple: [Speaker of the National Assembly of Kenya, legislativeHouseLevel, lower house]
-
A.
legislativeChamberLevel
chosen
Indicates the hierarchical level (e.g., national, state, local) at which a legislative chamber operates within a political or governmental system.
-
B.
legislativeBase
Indicates that one entity serves as the legal or legislative basis, authority, or foundation for another entity or action.
-
C.
parliamentaryHouse
Indicates that one entity functions as a parliamentary chamber or house within the legislative system of another entity.
-
D.
hasLegislatureType
Indicates the specific form or system of legislature that an entity possesses or operates under.
-
E.
legislatureNumber
Indicates the specific numbered session or term of a legislative body associated with an entity or event.
- 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_69ca831c45f08190ac1505cc15076608 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd79485881909df562bfff36ccf4 |
completed | April 2, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69cd4b7cd4208190b2253583ee2f892c |
completed | April 1, 2026, 4:44 p.m. |
Created at: March 30, 2026, 8:53 p.m.