Triple
T4841433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hail Mary |
E108188
|
entity |
| Predicate | petitionPhrase |
P59710
|
FINISHED |
| Object | pray for us sinners |
—
|
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: pray for us sinners | Statement: [Hail Mary, petitionPhrase, pray for us sinners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: petitionPhrase Context triple: [Hail Mary, petitionPhrase, pray for us sinners]
-
A.
petitionFormula
Indicates a formal written request or appeal made by one party to another, typically to an authority, following a specific formula or structured format.
-
B.
petition
Indicates that one entity formally requests or appeals to another entity, typically an authority, for a specific action or change.
-
C.
usedPhrase
Indicates that one entity employed or expressed a particular phrase in speech, writing, or another form of communication.
-
D.
refrainWord
Indicates that one entity avoids using, mentioning, or expressing a particular word or term in relation to another entity or context.
-
E.
featuresCatchphrase
Indicates that an entity prominently includes or is associated with a particular catchphrase.
- 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_69bd4409b264819085ab855f3eb5381a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e01872c81909607010c10538ad1 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2375a4819098e16acb982c8fab |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6dfff1488190a32bbb615bfab970 |
completed | March 20, 2026, 3:55 p.m. |
Created at: March 20, 2026, 1:25 p.m.