Triple
T22914384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kavita Krishnamurti |
E568688
|
entity |
| Predicate | notableCollaboration |
P8554
|
FINISHED |
| Object | Sonu Nigam |
—
|
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: Sonu Nigam | Statement: [Kavita Krishnamurti, notableCollaboration, Sonu Nigam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonu Nigam Context triple: [Kavita Krishnamurti, notableCollaboration, Sonu Nigam]
-
A.
Sonu Nigam
chosen
Sonu Nigam is a renowned Indian playback singer and live performer known for his versatile vocals across Bollywood, devotional, and pop music.
-
B.
Arijit Biswas
Arijit Biswas is an Indian screenwriter known for his work on acclaimed Hindi films, including the black comedy thriller "Andhadhun."
-
C.
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.
-
D.
Zubeen
Zubeen is a given name, typically used as a variant spelling of the name Zubin.
-
E.
Shekhar Suman
Shekhar Suman is an Indian actor, television host, and comedian known for his work in Hindi films and popular TV shows.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18078077881908b8124cc22110c6e |
completed | April 29, 2026, 3:52 a.m. |
Created at: April 17, 2026, 3:42 p.m.