Triple
T25843631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | صاد |
E651003
|
entity |
| Predicate | مقابل_لاتيني_تقريبي |
P15005
|
FINISHED |
| Object | ṣ |
—
|
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: ṣ | Statement: [صاد, مقابل_لاتيني_تقريبي, ṣ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: مقابل_لاتيني_تقريبي Context triple: [صاد, مقابل_لاتيني_تقريبي, ṣ]
-
A.
correspondsToLatinWord
Indicates that one element is the equivalent or matching term of another element in Latin.
-
B.
equivalentInZapotec
Indicates that two linguistic elements are equivalent in meaning or function within the Zapotec language.
-
C.
translationApproximate
chosen
Indicates that one entity is an inexact or approximate translation of another, preserving general meaning but not precise wording or full detail.
-
D.
latinTranslator
Indicates that one entity translates text or speech into Latin for another entity or context.
-
E.
correspondsToInArabic
Indicates that one entity is the equivalent or matching counterpart of another entity specifically in the Arabic language.
- 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_69e7ab38086081908f3a8e7e0c6efd83 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6023662a48190b8eb77eebc225c36 |
completed | May 2, 2026, 1:55 p.m. |
| PD | Predicate disambiguation | batch_69f4a0fed15881909b789251fe5d8d45 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 22, 2026, 7:51 a.m.