Triple
T23923534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | אברהם אבן עזרא |
E602282
|
entity |
| Predicate | כתב פירוש על |
P87652
|
FINISHED |
| Object | ספר בראשית |
—
|
NE NERFINISHED |
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: ספר בראשית | Statement: [אברהם אבן עזרא, כתב פירוש על, ספר בראשית]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: כתב פירוש על Context triple: [אברהם אבן עזרא, כתב פירוש על, ספר בראשית]
-
A.
writingMeaning
Indicates that one entity expresses or conveys a particular meaning through writing about another entity or topic.
-
B.
דיני כתיבה בו
Indicates that the subject is governed by the same halachic laws and requirements of writing that apply to it (e.g., that the laws of writing are operative in this context).
-
C.
شرحه
chosen
Indicates that one entity explains, interprets, or clarifies something to another entity.
-
D.
textMeaning
Indicates that one text expresses, conveys, or corresponds to a particular meaning or semantic content.
-
E.
inscriptionMeaning
Indicates that an inscription conveys a particular meaning, message, or content.
- 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_69e2953b928c819095395fa87baca583 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf1abd148190a8393418ed965019 |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:41 p.m.