Triple
T3496914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iltutmish |
E73872
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Razia Sultana |
E72690
|
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: Razia Sultana | Statement: [Iltutmish, child, Razia Sultana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Razia Sultana Context triple: [Iltutmish, child, Razia Sultana]
-
A.
Razia Sultana
chosen
Razia Sultana was the 13th-century ruler of the Delhi Sultanate and one of the first and most prominent female Muslim monarchs in South Asian history.
-
B.
Izz-un-Nissa Begum
Izz-un-Nissa Begum was a Mughal princess and one of Emperor Shah Jahan’s wives, known for her high rank and influence within the imperial harem.
-
C.
Lutf-un-nisa Begum
Lutf-un-nisa Begum was a Mughal-era noblewoman whose name appears in historical records of the imperial court.
-
D.
Sultan Begum
Sultan Begum is a historical female figure from the Mughal era, known primarily as a royal consort within the early Mughal imperial family.
-
E.
Maham Begum
Maham Begum was a chief consort of the Mughal emperor Babur and the mother of his successor, Humayun.
- 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_69ad85cdb6e48190a335d412b9194ed8 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbd16c0081908f13535f459618d1 |
completed | March 8, 2026, 6:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b48821c3388190957dfccdcbdfff40 |
completed | March 13, 2026, 9:56 p.m. |
Created at: March 8, 2026, 3:18 p.m.