Triple
T29104151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gothic forces |
E736716
|
entity |
| Predicate | religionOfManyWarriors |
P137031
|
FINISHED |
| Object | Arian Christianity |
—
|
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: Arian Christianity | Statement: [Gothic forces, religionOfManyWarriors, Arian Christianity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religionOfManyWarriors Context triple: [Gothic forces, religionOfManyWarriors, Arian Christianity]
-
A.
religionOfDefenders
Indicates the religious affiliation practiced or associated with the defenders in a given context.
-
B.
religionOfConquerors
Indicates that the specified religion is practiced or upheld by the conquering group or power in a given context.
-
C.
hasReligionOfBelligerents
chosen
Indicates that the belligerent parties in a conflict are associated with a particular religion or religious affiliation.
-
D.
religionOfKeyCommander
Indicates the religious affiliation associated with a key commander.
-
E.
hasWarDeity
Indicates that an entity has a specific deity associated with war as part of its religious or mythological system.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 28, 2026, 11:14 a.m.