Triple
T28936957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umayyad army |
E730342
|
entity |
| Predicate | paySource |
P8003
|
FINISHED |
| Object | state stipends from the diwan |
—
|
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: state stipends from the diwan | Statement: [Umayyad army, paySource, state stipends from the diwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paySource Context triple: [Umayyad army, paySource, state stipends from the diwan]
-
A.
pays
Indicates that one entity gives money or another form of compensation to another entity, typically in exchange for goods, services, or to settle a debt.
-
B.
payerType
Indicates the type or category of entity responsible for making a payment in the relationship.
-
C.
employerContributionSource
Indicates that a contribution originates from an employer as the paying or funding source.
-
D.
wealthSource
chosen
Indicates the relationship by which an entity obtains or derives its wealth from a particular source.
-
E.
payCategory
Indicates the classification of a payment or compensation into a specific category (such as type, purpose, or pay band) within a payment or payroll context.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65b57b2a88190b290fc422c508a7c |
completed | May 2, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 8:33 a.m.