Triple
T3152795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aleinu |
E65913
|
entity |
| Predicate | textualVariants |
P37815
|
FINISHED |
| Object | different versions in Ashkenazi and Sephardi rites |
—
|
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: different versions in Ashkenazi and Sephardi rites | Statement: [Aleinu, textualVariants, different versions in Ashkenazi and Sephardi rites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: textualVariants Context triple: [Aleinu, textualVariants, different versions in Ashkenazi and Sephardi rites]
-
A.
languageVariant
Indicates that one language is a variant, dialect, or localized form of another language.
-
B.
textualFamily
chosen
Indicates that two or more texts are related through a shared origin, tradition, or lineage, forming a recognizable textual group or family.
-
C.
linguisticVariant
Indicates that one linguistic form is an alternative version or expression of another within the same or closely related language context.
-
D.
orthographicVariant
Indicates that two written forms are different spellings or orthographic representations of the same linguistic item.
-
E.
textType
Indicates the classification of a text according to its type, format, or genre.
- 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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5c27258819099c46a657779780b |
completed | March 8, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfbf0348190952a6bca8fc5fed1 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:05 p.m.