Triple
T25803017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | נגב |
E649887
|
entity |
| Predicate | שפה רשמית |
P236
|
FINISHED |
| Object | עברית |
—
|
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: עברית | Statement: [נגב, שפה רשמית, עברית]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: שפה רשמית Context triple: [נגב, שפה רשמית, עברית]
-
A.
officialLanguage
chosen
Indicates that a particular language has been formally designated by an authority as the official language used for government, legal, or administrative purposes in a given jurisdiction.
-
B.
officialLanguageUse
Indicates that a particular language is formally designated and used by an authority (such as a government or institution) for official communication, documentation, or functions.
-
C.
shareOfficialLanguage
Indicates that two entities have at least one official language in common.
-
D.
standardLanguageOf
Indicates that one entity serves as the officially recognized or commonly used standard language for another entity (such as a country, region, or organization).
-
E.
writtenLanguage
Indicates that one entity uses or is expressed in a particular written language associated with the other entity.
- 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_69e7ab34f8c8819099f6c4dabdabf129 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5ffccd0d0819095d21378b5b9590a |
completed | May 2, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69f4938b960081909b53c074a3e0c7c2 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 6:42 a.m.