Triple
T36311880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Finance Act of Kenya |
E894086
|
entity |
| Predicate | timeOfEffect |
P28440
|
FINISHED |
| Object | specific financial year |
—
|
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: specific financial year | Statement: [Finance Act of Kenya, timeOfEffect, specific financial year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfEffect Context triple: [Finance Act of Kenya, timeOfEffect, specific financial year]
-
A.
effectDuration
Indicates the length of time for which an effect remains active or valid.
-
B.
temporalEffect
Indicates a relationship where one event, state, or action produces consequences or changes that occur at a later time.
-
C.
activationTime
chosen
Indicates the specific point in time at which an entity, process, or function becomes active or starts operating.
-
D.
tookEffect
Indicates that a change, rule, condition, or event became active, operative, or started producing its intended consequences.
-
E.
hadEffectUntil
Indicates that an effect or condition held true up to a specific time or event, after which it no longer applied.
- 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_69f76e4c1b248190b10667d0213537fe |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdd92396788190ae1424bc1ae55844 |
completed | May 8, 2026, 12:37 p.m. |
| PD | Predicate disambiguation | batch_69fdd678f40481909a717a2daec83b36 |
completed | May 8, 2026, 12:26 p.m. |
Created at: May 3, 2026, 4:09 p.m.