Triple
T30876135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alma the Younger |
E786479
|
entity |
| Predicate | priorToConversion |
P160577
|
FINISHED |
| Object | persecuted the church |
—
|
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: persecuted the church | Statement: [Alma the Younger, priorToConversion, persecuted the church]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: priorToConversion Context triple: [Alma the Younger, priorToConversion, persecuted the church]
-
A.
priorService
Indicates that one entity has previously provided service or served in a role, position, or capacity before the current context or event.
-
B.
priorPost
Indicates that one post occurs earlier in sequence or time relative to another post.
-
C.
classBeforeConversion
Indicates that one class existed in its original form prior to being transformed or converted into another class.
-
D.
preConversionPractice
chosen
Indicates a practice or activity that occurs before a conversion process takes place.
-
E.
convertedBefore
Indicates that one entity was converted or transformed into another form or state earlier in time than a second, comparable conversion.
- 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_69f224bae17c8190bb3a6a28e3d019df |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f691d6a90081908726a2218a51dc25 |
completed | May 3, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69f68b7d2794819092fef8a63f4f3de8 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:48 p.m.