Triple
T10814447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adh-Dhariyat |
E255187
|
entity |
| Predicate | transliteration |
P2508
|
FINISHED |
| Object | Adh-Dhāriyāt |
E255187
|
NE 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: Adh-Dhāriyāt | Statement: [Adh-Dhariyat, transliteration, Adh-Dhāriyāt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adh-Dhāriyāt Context triple: [Adh-Dhariyat, transliteration, Adh-Dhāriyāt]
-
A.
Adh-Dhariyat
chosen
Adh-Dhariyat is the 51st chapter (surah) of the Qur’an, known for its themes of divine power, resurrection, and the consequences of belief and disbelief.
-
B.
Adh-Dhahiriya
Adh-Dhahiriya is a Palestinian town in the southern West Bank known for its historic cave dwellings and agricultural character.
-
C.
As-Sami‘
As-Sami‘ is one of the 99 Names of Allah in Islam, signifying “The All-Hearing,” the One who hears every sound, supplication, and secret without limitation.
-
D.
Al Mashun
Al Mashun is the namesake of the Great Mosque of Medan, a prominent historic Islamic landmark in Medan, Indonesia.
-
E.
Dhuʼb
Dhuʼb is a subtribe historically associated with the larger Arab tribe of Kinana.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733ece4488190b553a66c4b5188bc |
completed | April 9, 2026, 5:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de8546b41081909e13152c4df2eb1c |
completed | April 14, 2026, 6:19 p.m. |
Created at: April 8, 2026, 9:18 p.m.