Triple
T12383548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | An-Naba |
E295802
|
entity |
| Predicate | positionInJuz |
P34330
|
FINISHED |
| Object | beginning of the 30th juzʼ |
—
|
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: beginning of the 30th juzʼ | Statement: [An-Naba, positionInJuz, beginning of the 30th juzʼ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInJuz Context triple: [An-Naba, positionInJuz, beginning of the 30th juzʼ]
-
A.
positionInMushaf
Indicates the specific location or ordering of a text segment within the physical or canonical arrangement of the Mushaf (written Qur’an).
-
B.
quranicJuz
chosen
Indicates that a specific portion or passage belongs to, or is contained within, a particular Juz (section) of the Quran.
-
C.
positionInVerse
Indicates the specific ordinal location that something occupies within a verse.
-
D.
quranPosition
Indicates the specific location or ordering of a referenced element within the text or structure of the Quran.
-
E.
positionInHebrewBible
Indicates the ordinal position that something occupies within the canonical sequence of books or passages in the Hebrew Bible.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbc3f608190b0ee3c4f304a94db |
completed | April 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.