Triple
T13834540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kongo |
E332489
|
entity |
| Predicate | convertedEliteReligion |
P11201
|
FINISHED |
| Object | Roman Catholicism |
—
|
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: Roman Catholicism | Statement: [Kongo, convertedEliteReligion, Roman Catholicism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convertedEliteReligion Context triple: [Kongo, convertedEliteReligion, Roman Catholicism]
-
A.
convertedToReligion
chosen
Indicates that an entity adopted or changed to a particular religion, typically from a previous belief system or lack thereof.
-
B.
laterRevertedReligion
Indicates that an entity adopted a religion and then subsequently reverted or returned to a previous or different religious affiliation.
-
C.
hadMajorReligion
Indicates that a particular religion was the primary or dominant faith practiced within a given entity (such as a region, state, or population) during a specified period.
-
D.
religionOfConquerors
Indicates that the specified religion is practiced or upheld by the conquering group or power in a given context.
-
E.
promotedReligion
Indicates that an entity actively supported, advocated for, or worked to spread a particular religion.
- 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de029a34bc8190ae892ef7b09fc9e9 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.