Triple

T11277619
Position Surface form Disambiguated ID Type / Status
Subject Tipu Sultan E266975 entity
Predicate spouse P13 FINISHED
Object Khadija Zaman Begum
Khadija Zaman Begum was a consort of Tipu Sultan, the 18th-century ruler of the Kingdom of Mysore in southern India.
 E916858 NE FINISHED

How this triple was built (4 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: Khadija Zaman Begum | Statement: [Tipu Sultan, spouse, Khadija Zaman Begum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Khadija Zaman Begum
Context triple: [Tipu Sultan, spouse, Khadija Zaman Begum]
  • A. Zulaikha Begum
    Zulaikha Begum was the mother of Maulana Abul Kalam Azad, the prominent Indian freedom fighter, Islamic scholar, and first Minister of Education of independent India.
  • B. Qudsia Begum
    Qudsia Begum was a Mughal royal consort and influential matriarch best known as the mother of Emperor Akbar II.
  • C. Dildar Begum
    Dildar Begum was a consort of the Mughal emperor Babur and the mother of his son Hindal Mirza.
  • D. Maryam Begum
    Maryam Begum was a Safavid royal woman best known as the mother of Shah Sultan Husayn, the last Safavid ruler of Iran.
  • E. 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.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Khadija Zaman Begum
Triple: [Tipu Sultan, spouse, Khadija Zaman Begum]
Generated description
Khadija Zaman Begum was a consort of Tipu Sultan, the 18th-century ruler of the Kingdom of Mysore in southern India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Khadija Zaman Begum
Target entity description: Khadija Zaman Begum was a consort of Tipu Sultan, the 18th-century ruler of the Kingdom of Mysore in southern India.
  • A. Zulaikha Begum
    Zulaikha Begum was the mother of Maulana Abul Kalam Azad, the prominent Indian freedom fighter, Islamic scholar, and first Minister of Education of independent India.
  • B. Qudsia Begum
    Qudsia Begum was a Mughal royal consort and influential matriarch best known as the mother of Emperor Akbar II.
  • C. Dildar Begum
    Dildar Begum was a consort of the Mughal emperor Babur and the mother of his son Hindal Mirza.
  • D. Maryam Begum
    Maryam Begum was a Safavid royal woman best known as the mother of Shah Sultan Husayn, the last Safavid ruler of Iran.
  • E. 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.
  • F. None of above. chosen

Provenance (5 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_69d6aac8c2f48190ad0596f1f89f0470 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e967ebb4819080b09ed3cec44e77 completed April 9, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69e50a0edcd081908547745d16d643ab completed April 19, 2026, 4:59 p.m.
NEDg Description generation batch_69e510f7bec08190989118b6e4a7fa49 completed April 19, 2026, 5:29 p.m.
NED2 Entity disambiguation (via description) batch_69e5168c8da0819093bf61d8ea5f9e35 completed April 19, 2026, 5:53 p.m.
Created at: April 8, 2026, 9:31 p.m.