Triple

T12118517
Position Surface form Disambiguated ID Type / Status
Subject Palace of Winds E288628 entity
Predicate alsoKnownAs P39 FINISHED
Object Hawa Mahal E57494 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: Hawa Mahal | Statement: [Palace of Winds, alsoKnownAs, Hawa Mahal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hawa Mahal
Context triple: [Palace of Winds, alsoKnownAs, Hawa Mahal]
  • A. Hawa Mahal chosen
    Hawa Mahal is an iconic pink sandstone palace in Jaipur, India, famed for its ornate façade with hundreds of small windows designed to allow royal women to observe street life unseen.
  • B. Darbar Mahal
    Darbar Mahal is a historic royal palace in Bahawalpur, Pakistan, renowned for its distinctive blend of Islamic and European architectural styles.
  • C. Gul Mahal
    Gul Mahal is a historic palace structure within Udaipur’s Jag Mandir complex, noted for its Mughal-influenced architecture and use as a royal retreat.
  • D. Pari Mahal
    Pari Mahal is a historic terraced garden and former Mughal-era royal observatory overlooking Dal Lake in Srinagar, India.
  • E. Takhat Vilas
    Takhat Vilas is an ornately decorated royal residence within Jodhpur’s Mehrangarh Fort, known for its vivid murals, glasswork, and blend of traditional and European design elements.
  • 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_69d6ab4a5c448190a110d1273314b21a completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915760d208190b68f5e024b3676ba completed April 10, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65e9868ec81909efd7e142d5fb090 completed May 2, 2026, 8:29 p.m.
Created at: April 8, 2026, 9:49 p.m.