Triple
T29982704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malaysian constitutional monarchy |
E761637
|
entity |
| Predicate | includesRuler |
P8405
|
FINISHED |
| Object | Sultan of Johor |
—
|
NE NERFINISHED |
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: Sultan of Johor | Statement: [Malaysian constitutional monarchy, includesRuler, Sultan of Johor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesRuler Context triple: [Malaysian constitutional monarchy, includesRuler, Sultan of Johor]
-
A.
involvesRuler
chosen
Indicates that the relationship or action includes or pertains to a ruler as a participating party.
-
B.
providedRulerFor
Indicates that one entity supplied or designated another entity to serve as the ruler or governing authority over a particular domain or group.
-
C.
recognizedAsRuler
Indicates that one entity is acknowledged or accepted by others as the legitimate ruler or sovereign authority.
-
D.
targetedRuler
Indicates that an entity intentionally directed hostile or coercive actions specifically against a ruling individual or authority figure.
-
E.
usedByRuler
Indicates that something is employed, utilized, or otherwise put to use by a ruler or governing authority.
- 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_69f2246851148190b8e76206db94b105 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a002f0839fc8190a874d3b0d0826d7e |
completed | May 10, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_6a002eae7b6481909974b321e2789b7e |
completed | May 10, 2026, 7:07 a.m. |
Created at: April 29, 2026, 6:35 p.m.