Triple
T8643926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | سورة الصافات |
E204724
|
entity |
| Predicate | تفتتح بالحروف |
P27928
|
FINISHED |
| Object | لا تفتتح بحروف مقطعة |
—
|
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: لا تفتتح بحروف مقطعة | Statement: [سورة الصافات, تفتتح بالحروف, لا تفتتح بحروف مقطعة]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: تفتتح بالحروف Context triple: [سورة الصافات, تفتتح بالحروف, لا تفتتح بحروف مقطعة]
-
A.
firstLetter
Indicates that one entity is the initial character or starting letter of another entity (typically a string or word).
-
B.
eachStanzaBeginsWithLetterOf
Indicates that every stanza in a text starts with a specific given letter.
-
C.
openingTo
Indicates that one entity serves as an entrance, access point, or passage leading into or toward 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.
openingLetters
chosen
Indicates that one entity is the initial or first letter(s) of another entity (such as a word, name, or string).
- 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_69ca834ca1c88190a11ffb0200342fac |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4798852881909c03c5eadf805e49 |
completed | March 31, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69cc455d6d448190a2da2a319ac78c37 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:28 p.m.