Triple

T1269966
Position Surface form Disambiguated ID Type / Status
Subject Shah Jahan E15686 entity
Predicate child P120 FINISHED
Object Dara Shikoh E99910 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: Dara Shikoh | Statement: [Shah Jahan, child, Dara Shikoh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dara Shikoh
Context triple: [Shah Jahan, child, Dara Shikoh]
  • A. Dara Shikoh chosen
    Dara Shikoh was a 17th-century Mughal prince and intellectual known for his efforts to promote religious syncretism between Islam and Hinduism, particularly through his translations of Hindu scriptures into Persian.
  • B. Mirza Sahiban
    Mirza Sahiban is a classic Punjabi tragic love story and folk romance that has been retold in poetry, song, and literature across generations.
  • C. Abu’l-Fazl ibn Mubarak
    Abu’l-Fazl ibn Mubarak was a prominent 16th-century Mughal historian, scholar, and statesman best known for authoring the Akbarnama and Ain-i-Akbari, detailed chronicles of Emperor Akbar’s reign.
  • D. Mirak Mirza Ghiyas
    Mirak Mirza Ghiyas was a Persian architect of the Mughal era, best known for introducing grand Persian garden-tomb design to India.
  • E. Shah Jahan
    Shah Jahan was a 17th-century Mughal emperor best known for commissioning the Taj Mahal and overseeing a golden age of Indo-Islamic art and architecture in India.
  • 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_69a4935a94308190bb92555b79032824 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4c0691d70819088e57c78ff34af1e completed March 1, 2026, 10:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69aca2f49a98819083dacff7e76ad195 completed March 7, 2026, 10:13 p.m.
Created at: March 1, 2026, 7:50 p.m.