Triple

T17422724
Position Surface form Disambiguated ID Type / Status
Subject Lal Qila E423656 entity
Predicate contains P35 FINISHED
Object Diwan-i-Khas NE NERFINISHED

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: Diwan-i-Khas | Statement: [Lal Qila, contains, Diwan-i-Khas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diwan-i-Khas
Context triple: [Lal Qila, contains, Diwan-i-Khas]
  • A. Diwan-i-Khas chosen
    Diwan-i-Khas is the ornate marble hall of private audience in Delhi’s Red Fort, where Mughal emperors once held exclusive court and state discussions.
  • B. Diwan-i-Khas
    Diwan-i-Khas is an ornate hall of private audience in Jaipur’s City Palace, renowned for its intricate Mughal-Rajput architecture and historic royal gatherings.
  • C. Diwan-e Kabir
    Diwan-e Kabir is a celebrated collection of mystical lyric poetry by the 13th-century Persian poet and Sufi mystic Rumi, inspired by his spiritual relationship with Shams-e Tabrizi.
  • D. Diwan-i-Makhfi
    Diwan-i-Makhfi is a celebrated Persian poetry collection attributed to Mughal princess and poet Zeb-un-Nissa, showcasing her mystical and lyrical verse.
  • E. Diwan-i-Aam
    Diwan-i-Aam is the historic public audience hall within Jaipur’s City Palace complex, where the rulers once addressed and interacted with their subjects.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44238b418819095c6a013d3ff3b17 completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.