Triple
T23736445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saudi judiciary |
E586552
|
entity |
| Predicate | recognizesLegalSource |
P65906
|
FINISHED |
| Object | royal decrees |
—
|
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 decrees | Statement: [Saudi judiciary, recognizesLegalSource, royal decrees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recognizesLegalSource Context triple: [Saudi judiciary, recognizesLegalSource, royal decrees]
-
A.
majorLegalSource
chosen
Indicates that one entity serves as a primary or authoritative legal basis or reference for another entity.
-
B.
legalCitation
Indicates that one legal document, case, or authority formally references or cites another as a source of legal support or precedent.
-
C.
legalAuthorityCited
Indicates that a particular legal authority (such as a statute, regulation, or case) is referenced or relied upon in relation to another legal document, argument, or decision.
-
D.
legalCitationSystem
Indicates a system or convention used to reference and identify legal authorities such as cases, statutes, or regulations.
-
E.
legalLicenseJurisdiction
Indicates the legal authority or geographic area under whose laws a particular license is granted, valid, or enforced.
- 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_69e24907dc9c8190be074c9c96a0ec2d |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bad28fa481909d7a6a6e98a7b0a5 |
completed | April 29, 2026, 8:01 a.m. |
| PD | Predicate disambiguation | batch_69f155f012808190a4b1cbc155558ade |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:10 p.m.