Triple
T1778654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galerius |
E39237
|
entity |
| Predicate | policyOnChristianity |
P7601
|
FINISHED |
| Object | initially severe persecution |
—
|
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: initially severe persecution | Statement: [Galerius, policyOnChristianity, initially severe persecution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyOnChristianity Context triple: [Galerius, policyOnChristianity, initially severe persecution]
-
A.
religionPolicy
chosen
Indicates the stance, rules, or approach an entity adopts toward religious beliefs, practices, or institutions.
-
B.
dominantReligionPolicy
Indicates the policy or stance an authority adopts toward the religion that holds dominant or majority status within a given context.
-
C.
religiousTarget
Indicates that an action, policy, or behavior is directed at someone or something specifically because of their religion or religious affiliation.
-
D.
theologicalFocus
Indicates that something is primarily concerned with, centered on, or directed toward theological themes, questions, or doctrines.
-
E.
religiousAffiliation
Indicates that one entity has a specified religious association, belief system, or denominational membership.
- 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_69a88630519c8190a17addd83c4a3ef4 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab74dc9d1481908084ef07872a71f8 |
completed | March 7, 2026, 12:44 a.m. |
| PD | Predicate disambiguation | batch_69aa61cf3ca881908641fd73ce2f7c9d |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:31 p.m.