Triple
T21944441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billu |
E541899
|
entity |
| Predicate | featuresCameoAppearanceBy |
P49662
|
FINISHED |
| Object | Kareena Kapoor |
—
|
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: Kareena Kapoor | Statement: [Billu, featuresCameoAppearanceBy, Kareena Kapoor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kareena Kapoor Context triple: [Billu, featuresCameoAppearanceBy, Kareena Kapoor]
-
A.
Kareena Kapoor Khan
chosen
Kareena Kapoor Khan is a prominent Indian film actress known for her versatile roles in Bollywood and her influential presence in contemporary Hindi cinema.
-
B.
Kajol
Kajol is a renowned Indian film actress celebrated for her powerful performances and iconic roles in Hindi cinema since the 1990s.
-
C.
Radhika Khanna
Radhika Khanna is known as the sister of Indian-American celebrity chef and restaurateur Vikas Khanna.
-
D.
Neha Kapur
Neha Kapur is an Indian model, former Miss India Universe 2006, and fashion entrepreneur.
-
E.
Vidya Balan
Vidya Balan is an acclaimed Indian actress known for her powerful performances in Hindi cinema and for pioneering strong, female-led films in Bollywood.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242688988190a7b8f033c49368de |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:56 p.m.