Triple
T22755542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neha Kakkar |
E562833
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Neha Kakkar |
—
|
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: Neha Kakkar | Statement: [Neha Kakkar, name, Neha Kakkar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neha Kakkar Context triple: [Neha Kakkar, name, Neha Kakkar]
-
A.
Neha Kakkar
chosen
Neha Kakkar is a popular Indian playback singer known for her hit Bollywood songs and energetic vocal style.
-
B.
Sunidhi Chauhan
Sunidhi Chauhan is a prominent Indian playback singer known for her powerful, versatile voice and numerous hit songs across Bollywood films.
-
C.
Shreya Ghoshal
Shreya Ghoshal is a renowned Indian playback singer celebrated for her versatile voice and extensive work across multiple Indian film industries.
-
D.
Tony Kakkar
Tony Kakkar is an Indian singer, composer, and music producer known for his work in Hindi pop and Bollywood music.
-
E.
Simi Garewal
Simi Garewal is an Indian actress and television personality known for her work in Hindi cinema and for hosting the popular talk show "Rendezvous with Simi Garewal."
- 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_69e24551ec7881909a9c924dbea155f6 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f179bc48788190b3deb9287d02cb2c |
completed | April 29, 2026, 3:23 a.m. |
Created at: April 17, 2026, 3:25 p.m.