Triple
T3461258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Avinu Malkeinu |
E73028
|
entity |
| Predicate | invokesAttribute |
P30406
|
FINISHED |
| Object | Divine mercy |
—
|
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: Divine mercy | Statement: [Avinu Malkeinu, invokesAttribute, Divine mercy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: invokesAttribute Context triple: [Avinu Malkeinu, invokesAttribute, Divine mercy]
-
A.
usesAttribute
chosen
Indicates that one entity employs, relies on, or makes use of a specific attribute of another entity in performing an action or defining a relationship.
-
B.
invokedIn
Indicates that an action, method, or function is called or executed within the context or body of another construct (such as a method, block, or scope).
-
C.
invocationType
Indicates the manner or mode in which an action, function, or process is called, triggered, or executed.
-
D.
attributesEventTo
Indicates assigning responsibility, origin, or cause of an event to a particular entity.
-
E.
invokesPrinciple
Indicates that one entity calls upon, applies, or relies on a particular principle as the basis for an action, decision, or reasoning process.
- 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_69ad85b224d481908ff8be51338d24ff |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbae745e081909007cd3a664c57f3 |
completed | March 8, 2026, 6:07 p.m. |
| PD | Predicate disambiguation | batch_69adae05bb0081909dc7e4779d6e05ef |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:17 p.m.