Triple
T32716024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan of Pahang on state legislative matters |
E836522
|
entity |
| Predicate | exercisesThrough |
P86881
|
FINISHED |
| Object | royal assent |
—
|
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: royal assent | Statement: [Sultan of Pahang on state legislative matters, exercisesThrough, royal assent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exercisesThrough Context triple: [Sultan of Pahang on state legislative matters, exercisesThrough, royal assent]
-
A.
exercisesWith
Indicates that two or more entities engage in physical exercise or workout activities together.
-
B.
exerciseOf
Indicates the performance or carrying out of a right, power, function, or activity by an entity.
-
C.
alsoExercises
Indicates that one entity engages in physical exercise in addition to, or alongside, another referenced entity.
-
D.
exercisesRightsThrough
chosen
Indicates that one party holds certain rights and actively exercises or enforces them through another party or mechanism.
-
E.
coreExercise
Indicates that an exercise primarily targets and engages the muscles of the core or midsection.
- 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_69f34935455881909088975d79460418 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c885d48c8190ae96ba6f46fe189a |
completed | May 3, 2026, 4:01 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f617c08190a70ba880210f908c |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:11 a.m.