Triple

T14003653
Position Surface form Disambiguated ID Type / Status
Subject Gawhar Shad E336891 entity
Predicate title P38 FINISHED
Object Gawhar Shad Begum E1073625 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: Gawhar Shad Begum | Statement: [Gawhar Shad, title, Gawhar Shad Begum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gawhar Shad Begum
Context triple: [Gawhar Shad, title, Gawhar Shad Begum]
  • A. Kandahari Begum
    Kandahari Begum was a Mughal princess and the first wife of Emperor Shah Jahan, known for her Timurid lineage and political significance in the Mughal court.
  • B. Khayr al-Nisa Begum
    Khayr al-Nisa Begum was a prominent Safavid royal consort and influential queen mother in early 17th-century Iran.
  • 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. Shah Begum
    Shah Begum was a Timurid-era noblewoman known as the daughter of Qutlugh Nigar Khanum and a member of the Mughal imperial family.
  • E. Goharshad Begum chosen
    Goharshad Begum was a powerful and influential Timurid queen consort and patron of architecture and the arts in 15th-century Persia.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed1d2548190bb46d6b7cba4ffde completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd095ca5081908d7fed82e9ef0252 completed May 7, 2026, 5:49 p.m.
Created at: April 9, 2026, 10:19 p.m.