Triple
T33457453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ابن جني |
E856815
|
entity |
| Predicate | موضوع كتاب اللمع في العربية |
P177411
|
FINISHED |
| Object | قواعد النحو والصرف |
—
|
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: قواعد النحو والصرف | Statement: [ابن جني, موضوع كتاب اللمع في العربية, قواعد النحو والصرف]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: موضوع كتاب اللمع في العربية Context triple: [ابن جني, موضوع كتاب اللمع في العربية, قواعد النحو والصرف]
-
A.
موضوع كتاب سر صناعة الإعراب
Indicates that the subject or topic under discussion is the book "Sir Ṣināʿat al-Iʿrāb" (The Secret of the Craft of Parsing).
-
B.
لغة السورة
Indicates the language in which a given surah (chapter of the Qur’an) is expressed or written.
-
C.
titleInArabic
Indicates that an entity’s title is expressed in the Arabic language.
-
D.
تذكر كتاب الأبرار
Indicates that an entity recalls or mentions the book of the righteous.
-
E.
حكم تلاوتها
Indicates the ruling or legal judgment regarding the recitation of something (e.g., whether its recitation is obligatory, recommended, permissible, disliked, or forbidden).
- F. None of above. chosen
Provenance (4 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_69f3497281a08190b4705de0b5f26ba7 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb93224881908fc66fe76115fcdb |
completed | May 3, 2026, 7:38 a.m. |
| PD | Predicate disambiguation | batch_69f6f96badb08190994442c2aba840b1 |
completed | May 3, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f6fb17d5ec81909091e37e1ddbe577 |
completed | May 3, 2026, 7:36 a.m. |
Created at: May 1, 2026, 1:37 a.m.