Triple
T25843626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | صاد |
E651003
|
entity |
| Predicate | شكل_في_أول_الكلمة |
P3818
|
FINISHED |
| Object | صـ |
—
|
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: صـ | Statement: [صاد, شكل_في_أول_الكلمة, صـ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: شكل_في_أول_الكلمة Context triple: [صاد, شكل_في_أول_الكلمة, صـ]
-
A.
firstWord
Indicates that one entity is the first word in the sequence or text associated with another entity.
-
B.
firstLetter
chosen
Indicates that one entity is the initial character or starting letter of another entity (typically a string or word).
-
C.
الشكل
Indicates a relationship where one entity represents, takes, or describes the form, shape, or configuration of another entity.
-
D.
firstWordsOf
Indicates that one entity consists of the initial word or sequence of words taken from another entity (such as a text or utterance).
-
E.
firstSyllable
Indicates that one entity is the first syllable occurring at the beginning of another entity (typically a word or phrase).
- 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_69f4938b960081909b53c074a3e0c7c2 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 7:51 a.m.