Triple
T21424375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | وزارة الدفاع |
E528514
|
entity |
| Predicate | لغة_العمل |
P125070
|
FINISHED |
| Object | العربية |
—
|
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: العربية | Statement: [وزارة الدفاع, لغة_العمل, العربية]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: لغة_العمل Context triple: [وزارة الدفاع, لغة_العمل, العربية]
-
A.
primaryLanguageInWork
Indicates that a specified language is the main or predominant language used within a particular work (such as a book, film, or document).
-
B.
workLanguageOfTitle
Indicates the language in which a specific work or title is expressed or written.
-
C.
languageOfUnderlyingWork
Indicates the language in which the original or underlying work (from which a derived or related work stems) is expressed.
-
D.
languageWithinWork
chosen
Indicates that a specific language is used or contained within a particular work (such as a document, publication, or creative piece).
-
E.
workLanguageVariant
Indicates that one language variant of a work is related to another version of the same work, typically differing by language or localization.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee813b798c8190a379cbf6cc6e14d2 |
completed | April 26, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e61639ee288190889ffd500d1260f6 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 5:48 p.m.