Triple
T21614255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sitt al-Mulk |
E533392
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | al-ʿAzīz bi-llāh |
—
|
NE NERFINISHED |
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: al-ʿAzīz bi-llāh | Statement: [Sitt al-Mulk, father, al-ʿAzīz bi-llāh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: al-ʿAzīz bi-llāh Context triple: [Sitt al-Mulk, father, al-ʿAzīz bi-llāh]
-
A.
Al-Aziz
Al-Aziz is one of the traditional Islamic Names of God, signifying the Almighty who is all-powerful, invincible, and exalted in might.
-
B.
al-ʿAzīz Billāh
chosen
al-ʿAzīz Billāh was a 10th-century Fatimid caliph who consolidated Fatimid rule in Egypt and expanded their influence across the eastern Mediterranean.
-
C.
al-Malik al-ʿAzīz
al-Malik al-ʿAzīz was the regnal title of Al-Aziz Uthman, an Ayyubid ruler and son of Saladin who governed parts of the medieval Islamic empire.
-
D.
Abū Zakarīyāʾ
Abū Zakarīyāʾ is the kunya (honorific name) of the renowned early Arabic grammarian and philologist Al-Farrāʾ, a leading figure of the Kufan school of grammar.
-
E.
ʿAzīz
ʿAzīz is an Arabic male given name and epithet meaning “mighty,” “dear,” or “beloved,” commonly used across the Muslim world.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46411108190bba0d4176dffc9f3 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef3ba9aca48190b5180eefd61a9fdc |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 16, 2026, 6:33 p.m.