Triple
T31248437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ספר בראשית |
E796750
|
entity |
| Predicate | פותח במילים |
P58461
|
FINISHED |
| Object | בראשית ברא אלהים את השמים ואת הארץ |
—
|
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: בראשית ברא אלהים את השמים ואת הארץ | Statement: [ספר בראשית, פותח במילים, בראשית ברא אלהים את השמים ואת הארץ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: פותח במילים Context triple: [ספר בראשית, פותח במילים, בראשית ברא אלהים את השמים ואת הארץ]
-
A.
عدد كلماتها التقريبي
Indicates an approximate count of the number of words associated with an entity.
-
B.
openingWordsHebrew
chosen
Indicates that the specified words are the opening (initial) words of a text or passage in Hebrew.
-
C.
لغة السورة
Indicates the language in which a given surah (chapter of the Qur’an) is expressed or written.
-
D.
isPlayOnWordsWith
Indicates a relationship where one expression is a pun or wordplay that depends on, echoes, or cleverly twists the wording or meaning of another expression.
-
E.
languageOfPoetry
Indicates that a specified language is the language in which a given piece of poetry is written or expressed.
- 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:11 p.m.