Triple
T24812497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | siege of Diriyah |
E620825
|
entity |
| Predicate | commanderForSaudiSide |
P68449
|
FINISHED |
| Object | Abdullah bin Saud |
—
|
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: Abdullah bin Saud | Statement: [siege of Diriyah, commanderForSaudiSide, Abdullah bin Saud]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commanderForSaudiSide Context triple: [siege of Diriyah, commanderForSaudiSide, Abdullah bin Saud]
-
A.
IraqiCommander
Indicates a relationship where an individual serves in the role of a military commander for Iraqi armed or security forces.
-
B.
ArabCommander
Indicates that the subject serves as a military commander associated with Arab forces or entities.
-
C.
sideCommander
chosen
Indicates that an entity serves as the commanding officer or leader in charge of a particular side or faction in a conflict, operation, or organization.
-
D.
commanderForGovernment
Indicates that an entity serves as a military or organizational commander on behalf of, or within the authority structure of, a specific government.
-
E.
commanderOfTurkishForces
Indicates that one entity serves as the commanding officer of Turkish military forces 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_69e2fabfd4648190bd0e5c7f4dbb6cab |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 4:51 a.m.