Triple
T31428475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman military institutions |
E801729
|
entity |
| Predicate | hasPaySystem |
P21821
|
FINISHED |
| Object | stipendium |
—
|
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: stipendium | Statement: [Roman military institutions, hasPaySystem, stipendium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPaySystem Context triple: [Roman military institutions, hasPaySystem, stipendium]
-
A.
hasPaymentOption
Indicates that an entity supports or offers a particular method or option for making payments.
-
B.
paySystem
Indicates that one entity provides monetary or other compensation to another entity through a particular method, platform, or mechanism.
-
C.
paymentSystem
chosen
Indicates a relationship where one entity functions as a mechanism or platform through which another entity makes or processes payments.
-
D.
hasPaymentModel
Indicates that an entity uses, is associated with, or operates under a particular payment model or pricing scheme.
-
E.
hasPayStatus
Indicates the current payment state or condition associated with an entity, such as whether an amount is paid, unpaid, pending, or otherwise resolved.
- 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_69f348c475348190bf579ca858eec77c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69feb342994081909481ec8ec5d44928 |
completed | May 9, 2026, 4:08 a.m. |
| PD | Predicate disambiguation | batch_69feb046e4e48190b96649aa28529cc9 |
completed | May 9, 2026, 3:55 a.m. |
Created at: April 30, 2026, 8:55 p.m.