Triple
T15321348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umar Sheikh Mirza II |
E366297
|
entity |
| Predicate | spouseOf |
P13
|
FINISHED |
| Object | Umid Bega Begum |
E366297
|
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: Umid Bega Begum | Statement: [Umar Sheikh Mirza II, spouseOf, Umid Bega Begum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Umid Bega Begum Context triple: [Umar Sheikh Mirza II, spouseOf, Umid Bega Begum]
-
A.
Umid Bega Begum
chosen
Umid Bega Begum was a Timurid noblewoman known primarily as a wife of Umar Sheikh Mirza II and thus a member of the Mughal imperial family’s ancestral lineage.
-
B.
Mahlara Begum
Mahlara Begum was a consort of the Mughal emperor Akbar II during the late Mughal period in India.
-
C.
Dildar Begum
Dildar Begum was a consort of the Mughal emperor Babur and the mother of his son Hindal Mirza.
-
D.
Rifa’at Begum
Rifa’at Begum was the wife of Iskander Mirza, the first President of Pakistan, and thus served as Pakistan’s First Lady during his tenure.
-
E.
Wafa Begum
Wafa Begum was a queen consort of the Durrani Empire as the wife of Afghan ruler Shuja Shah Durrani.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd460288190b5c41f0a0aeee949 |
completed | April 16, 2026, 1:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff755e0f2c819088293d8a55d7883a |
completed | May 9, 2026, 5:56 p.m. |
Created at: April 10, 2026, 3:16 a.m.