Triple

T17704393
Position Surface form Disambiguated ID Type / Status
Subject In Custody E441391 entity
Predicate featuresCharacter P626 FINISHED
Object Imtiaz Begum
Imtiaz Begum is a character in the Pakistani television drama "In Custody."
E1283802 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: Imtiaz Begum | Statement: [In Custody, featuresCharacter, Imtiaz Begum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Imtiaz Begum
Context triple: [In Custody, featuresCharacter, Imtiaz Begum]
  • A. Munny Begum
    Munny Begum was a prominent consort of Nawab Mir Jafar of Bengal who wielded considerable influence in the late 18th-century Nawabi court.
  • B. Asmat Begum
    Asmat Begum was a Mughal noblewoman and relative of Empress Nur Jahan, remembered primarily for her association with the imperial family and her burial in the famed Itmad-ud-Daulah's Tomb in Agra.
  • C. Wafa Begum
    Wafa Begum was a queen consort of the Durrani Empire as the wife of Afghan ruler Shuja Shah Durrani.
  • 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. Gauhar Ara Begum
    Gauhar Ara Begum was a Mughal princess, the daughter of Emperor Shah Jahan and his famed consort Mumtaz Mahal, and a member of the imperial family during the empire’s zenith in 17th-century India.
  • 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: Imtiaz Begum
Triple: [In Custody, featuresCharacter, Imtiaz Begum]
Generated description
Imtiaz Begum is a character in the Pakistani television drama "In Custody."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Imtiaz Begum
Target entity description: Imtiaz Begum is a character in the Pakistani television drama "In Custody."
  • A. Munny Begum
    Munny Begum was a prominent consort of Nawab Mir Jafar of Bengal who wielded considerable influence in the late 18th-century Nawabi court.
  • B. Asmat Begum
    Asmat Begum was a Mughal noblewoman and relative of Empress Nur Jahan, remembered primarily for her association with the imperial family and her burial in the famed Itmad-ud-Daulah's Tomb in Agra.
  • C. Wafa Begum
    Wafa Begum was a queen consort of the Durrani Empire as the wife of Afghan ruler Shuja Shah Durrani.
  • 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. Gauhar Ara Begum
    Gauhar Ara Begum was a Mughal princess, the daughter of Emperor Shah Jahan and his famed consort Mumtaz Mahal, and a member of the imperial family during the empire’s zenith in 17th-century India.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47296770c8190b6b172fb647da564 completed April 19, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a023022e50881908a617d2f80e00956 completed May 11, 2026, 7:38 p.m.
NEDg Description generation batch_6a0231b6005c8190a1d7aa10a61fa7b9 completed May 11, 2026, 7:44 p.m.
NED2 Entity disambiguation (via description) batch_6a023228e064819095b1d73d0fd2c3c2 completed May 11, 2026, 7:46 p.m.
Created at: April 10, 2026, 10:05 a.m.