Triple

T6296504
Position Surface form Disambiguated ID Type / Status
Subject Alka Yagnik E141143 entity
Predicate hasPerformedWith P9966 FINISHED
Object Kumar Sanu
Kumar Sanu is a renowned Indian playback singer, especially famous for his melodious and prolific contributions to Bollywood film music in the 1990s.
E636138 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: Kumar Sanu | Statement: [Alka Yagnik, hasPerformedWith, Kumar Sanu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kumar Sanu
Context triple: [Alka Yagnik, hasPerformedWith, Kumar Sanu]
  • A. Udit Narayan
    Udit Narayan is a renowned Indian playback singer celebrated for his melodious voice and numerous hit songs in Bollywood films since the 1980s.
  • B. Sonu Nigam
    Sonu Nigam is a renowned Indian playback singer and live performer known for his versatile vocals across Bollywood, devotional, and pop music.
  • C. Alka Yagnik
    Alka Yagnik is a renowned Indian playback singer celebrated for her melodious voice and numerous hit songs in Hindi cinema since the 1980s.
  • D. Kishore Kumar
    Kishore Kumar was a legendary Indian playback singer, actor, and music composer renowned for his versatile voice and iconic songs in Hindi cinema.
  • E. Sad-bhawna Shikhar
    Sad-bhawna Shikhar is a peak in central India that forms the highest elevation of the Vindhya Range.
  • 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: Kumar Sanu
Triple: [Alka Yagnik, hasPerformedWith, Kumar Sanu]
Generated description
Kumar Sanu is a renowned Indian playback singer, especially famous for his melodious and prolific contributions to Bollywood film music in the 1990s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kumar Sanu
Target entity description: Kumar Sanu is a renowned Indian playback singer, especially famous for his melodious and prolific contributions to Bollywood film music in the 1990s.
  • A. Udit Narayan
    Udit Narayan is a renowned Indian playback singer celebrated for his melodious voice and numerous hit songs in Bollywood films since the 1980s.
  • B. Sonu Nigam
    Sonu Nigam is a renowned Indian playback singer and live performer known for his versatile vocals across Bollywood, devotional, and pop music.
  • C. Alka Yagnik
    Alka Yagnik is a renowned Indian playback singer celebrated for her melodious voice and numerous hit songs in Hindi cinema since the 1980s.
  • D. Kishore Kumar
    Kishore Kumar was a legendary Indian playback singer, actor, and music composer renowned for his versatile voice and iconic songs in Hindi cinema.
  • E. Sad-bhawna Shikhar
    Sad-bhawna Shikhar is a peak in central India that forms the highest elevation of the Vindhya Range.
  • 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_69c008cdf2ac8190bb640c94478fb4ed completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0643ac2b48190b2db036ce709e7ea completed March 22, 2026, 9:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c77510f80c81908fe7784bdaa640c5 completed March 28, 2026, 6:28 a.m.
NEDg Description generation batch_69c777671e248190b0b9a38f798446d9 completed March 28, 2026, 6:38 a.m.
NED2 Entity disambiguation (via description) batch_69c777c80d6c8190b4e7cd0243c9042e completed March 28, 2026, 6:40 a.m.
Created at: March 22, 2026, 4:27 p.m.