Triple
T31685258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qur’an 46:13 |
E808640
|
entity |
| Predicate | neighboringVerseBefore |
P122360
|
FINISHED |
| Object | Qur’an 46:12 |
—
|
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: Qur’an 46:12 | Statement: [Qur’an 46:13, neighboringVerseBefore, Qur’an 46:12]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: neighboringVerseBefore Context triple: [Qur’an 46:13, neighboringVerseBefore, Qur’an 46:12]
-
A.
neighboringVersePrevious
chosen
Indicates that one verse immediately precedes another verse in sequence, making it the previous neighboring verse.
-
B.
neighboringVerseNext
Indicates that one verse directly follows another verse in sequence, making them adjacent neighbors in the text.
-
C.
verseBefore
Indicates that one verse occurs earlier in the ordered sequence of verses than another verse.
-
D.
verseAfter
Indicates that one verse occurs immediately later in sequence than another verse within the same ordered text.
-
E.
previousSentence
Indicates that one sentence directly precedes another in a sequence of text.
- 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_69f348ddcbc48190950cabcc25ff29b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 30, 2026, 11:06 p.m.