Triple
T18218950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decius |
E436240
|
entity |
| Predicate | policyDetail |
P130292
|
FINISHED |
| Object | required all inhabitants of the empire to perform sacrifices to the Roman gods |
—
|
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: required all inhabitants of the empire to perform sacrifices to the Roman gods | Statement: [Decius, policyDetail, required all inhabitants of the empire to perform sacrifices to the Roman gods]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyDetail Context triple: [Decius, policyDetail, required all inhabitants of the empire to perform sacrifices to the Roman gods]
-
A.
policyName
Indicates the specific name or title assigned to a policy associated with an entity.
-
B.
policyOutput
Indicates that a policy or decision-making process produces or yields a particular outcome, result, or output.
-
C.
policyCharacteristic
Indicates that a policy possesses a particular attribute, feature, or quality that characterizes how it is defined or operates.
-
D.
policyElement
Indicates that something is a component or constituent part of a broader policy.
-
E.
policyLevel
Indicates the degree or tier of strictness, scope, or priority associated with a given policy.
- F. None of above. chosen
Provenance (4 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_69d8b9103a8081908bbb0836fef10efd |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e47926988190802c00b074cdc696 |
completed | April 19, 2026, 2:19 p.m. |
| PD | Predicate disambiguation | batch_69e4332155d88190b106d0dceb4554af |
completed | April 19, 2026, 1:42 a.m. |
| PDg | Predicate description generation | batch_69e438f684e48190b38c64b58c518b6a |
completed | April 19, 2026, 2:07 a.m. |
Created at: April 10, 2026, 10:32 a.m.