Triple
T15307852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomb of Hayat Bakshi Begum |
E365948
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Hayat Bakshi Begum |
E1170040
|
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: Hayat Bakshi Begum | Statement: [Tomb of Hayat Bakshi Begum, namedAfter, Hayat Bakshi Begum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hayat Bakshi Begum Context triple: [Tomb of Hayat Bakshi Begum, namedAfter, Hayat Bakshi Begum]
-
A.
Hayat Bakshi Begum
chosen
Hayat Bakshi Begum was an influential 17th-century queen and political figure of the Qutb Shahi dynasty in the Deccan region of India, renowned for her patronage of architecture and governance.
-
B.
Gul Hayat Begum
Gul Hayat Begum was the wife of prominent Sindhi nationalist leader and intellectual G. M. Syed.
-
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.
Diwanji Begum
Diwanji Begum was a Mughal noblewoman best known as the mother of Mumtaz Mahal, the empress for whom the Taj Mahal was built.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd001b48190bbdd69337efdb907 |
completed | April 16, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ec2f35c8190a96af080cd7b6d0e |
completed | May 9, 2026, 5:28 p.m. |
Created at: April 10, 2026, 3:16 a.m.