Triple
T8990303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | خادم الحرمين الشريفين |
E214770
|
entity |
| Predicate | مرتبط_بنظام |
P32380
|
FINISHED |
| Object | الملكية المطلقة في السعودية |
—
|
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: الملكية المطلقة في السعودية | Statement: [خادم الحرمين الشريفين, مرتبط_بنظام, الملكية المطلقة في السعودية]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: مرتبط_بنظام Context triple: [خادم الحرمين الشريفين, مرتبط_بنظام, الملكية المطلقة في السعودية]
-
A.
associatedSystem
chosen
Indicates that one entity is functionally or contextually linked to a particular system with which it interacts or to which it belongs.
-
B.
bondedWith
Indicates that two entities are joined by a strong, enduring connection or attachment, whether emotional, social, or structural.
-
C.
hasCorrelativesSystem
Indicates that one entity possesses or employs a system of correlatives—structured, corresponding elements or forms that are systematically related to each other.
-
D.
relatedType
Indicates that one entity is connected to another through a specified type or category of relationship.
-
E.
ligadoA
Indicates that one entity is connected, linked, or otherwise associated with another entity.
- 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_69ca839f76bc8190a4b7123cdd682199 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc68733548819096a5ba0ff41e43da |
completed | April 1, 2026, 12:36 a.m. |
| PD | Predicate disambiguation | batch_69cc5edba0f88190b97401636a076d7a |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:04 p.m.