Triple
T3815934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marian apparitions |
E84253
|
entity |
| Predicate | possibleJudgment |
P52041
|
FINISHED |
| Object | approved as worthy of belief |
—
|
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: approved as worthy of belief | Statement: [Marian apparitions, possibleJudgment, approved as worthy of belief]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleJudgment Context triple: [Marian apparitions, possibleJudgment, approved as worthy of belief]
-
A.
possibleRelative
Indicates a relationship where one entity may be related to another by family or kinship, but the exact nature of the relationship is uncertain or not fully established.
-
B.
judgeFrom
Indicates that one entity forms an opinion, evaluation, or conclusion about something based on another specified source, basis, or perspective.
-
C.
judgmentInvolves
Indicates that a particular judgment, decision, or legal ruling includes, concerns, or pertains to a specified entity or matter.
-
D.
couldPass
Indicates that one entity had the ability or potential to move through, overcome, or be accepted by another entity or barrier.
-
E.
judgesMayBe
Indicates that certain individuals can serve in the role of judges under specified conditions or classifications.
- 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_69aed931f5908190be2c07af66d4df25 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef1515c688190a38332aedeed8a76 |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee7482d708190a3ec74745b102a4c |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aef14f9bb4819098e64b527b546d74 |
completed | March 9, 2026, 4:11 p.m. |
Created at: March 9, 2026, 3:17 p.m.