Triple
T30501295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | الشرقاط |
E776142
|
entity |
| Predicate | تتبع إدارياً |
P56871
|
FINISHED |
| Object | محافظة صلاح الدين |
—
|
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: محافظة صلاح الدين | Statement: [الشرقاط, تتبع إدارياً, محافظة صلاح الدين]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: تتبع إدارياً Context triple: [الشرقاط, تتبع إدارياً, محافظة صلاح الدين]
-
A.
followedAdministrativeModelOf
Indicates that one entity adopted or implemented its administrative structure, procedures, or governance framework based on the administrative model used by another entity.
-
B.
تتبع_عقيدة
Indicates that one entity follows, adheres to, or subscribes to a particular doctrine or creed associated with another entity.
-
C.
administrativelyIn
chosen
Indicates that one entity is located within or belongs to the jurisdiction or governance area of another entity for administrative purposes.
-
D.
typeOfAdministration
Indicates the specific form or system of administration applied to or governing an entity.
-
E.
investigatedAdministration
Indicates that an entity conducted an investigation into the actions, conduct, or operations of an administration.
- 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_69f22498c5d481908aaea89e6fab8280 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f687805b048190824b5c0bc8d09bab |
completed | May 2, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:14 p.m.