Triple
T21662581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rinke Khanna |
E534628
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Twinkle Khanna |
—
|
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: Twinkle Khanna | Statement: [Rinke Khanna, sibling, Twinkle Khanna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Twinkle Khanna Context triple: [Rinke Khanna, sibling, Twinkle Khanna]
-
A.
Twinkle Khanna
chosen
Twinkle Khanna is an Indian author, columnist, interior designer, and former Bollywood actress known for her witty writing and bestselling books.
-
B.
Radhika Khanna
Radhika Khanna is known as the sister of Indian-American celebrity chef and restaurateur Vikas Khanna.
-
C.
Kiara Advani
Kiara Advani is an Indian film actress known for her work in Hindi and Telugu cinema, with notable roles in films like "Kabir Singh," "Shershaah," and "MS Dhoni: The Untold Story."
-
D.
Sanya Malhotra
Sanya Malhotra is an Indian actress known for her acclaimed debut in the film "Dangal" and subsequent roles in Hindi cinema.
-
E.
Shweta Bachchan Nanda
Shweta Bachchan Nanda is an Indian author, columnist, and fashion designer, known as the daughter of legendary actor Amitabh Bachchan and for her work in media and luxury fashion.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef6c0956e0819093b4794418efe052 |
completed | April 27, 2026, 2 p.m. |
Created at: April 16, 2026, 6:36 p.m.