Triple
T2998698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purim Katan |
E81132
|
entity |
| Predicate | associatedVerse |
P15334
|
FINISHED |
| Object | Mishlei 15:15 |
—
|
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: Mishlei 15:15 | Statement: [Purim Katan, associatedVerse, Mishlei 15:15]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedVerse Context triple: [Purim Katan, associatedVerse, Mishlei 15:15]
-
A.
verses
Indicates a relationship where one entity competes or is pitted against another, as in an opposition, matchup, or comparison.
-
B.
containsVerse
Indicates that one entity (typically a text or collection) includes a specific verse as part of its content.
-
C.
keyVerse
chosen
Indicates that one verse is designated as the central or most thematically important verse in relation to a text, passage, or concept.
-
D.
scriptureAllusion
Indicates that one entity makes reference to, echoes, or is inspired by a passage, theme, or element from a scriptural text found in another entity.
-
E.
associatedWithVerb
Indicates that one entity is connected or linked to another through some verb-based relationship or action.
- 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_69ad8b187fc8819085914d3c9ea3142d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad99f766408190a5591efce8346bb9 |
completed | March 8, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69ad9615fefc8190ad96da92519cb7a3 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:59 p.m.