Triple
T10020985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constitution of Kenya |
E200606
|
entity |
| Predicate | previousConstitutionYear |
P29693
|
FINISHED |
| Object | 1963 |
—
|
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: 1963 | Statement: [Constitution of Kenya, previousConstitutionYear, 1963]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousConstitutionYear Context triple: [Constitution of Kenya, previousConstitutionYear, 1963]
-
A.
previousConstitution
Indicates that one constitution temporally precedes and was in force before another constitution in a given legal or political system.
-
B.
previousConstitutionRevised
Indicates that a prior constitution has been modified or updated through a formal revision process.
-
C.
lastConstitutionAdopted
Indicates that a particular constitution was the most recently adopted constitution of a given political entity or jurisdiction.
-
D.
earliestConstitutionAdopted
Indicates that one entity is the constitution that was adopted first in time among all constitutions associated with another entity.
-
E.
servedAsConstitutionUntil
chosen
Indicates that one document functioned as the official constitution of an entity up to a specified point in time.
- 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.