Triple
T22433236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lootera |
E554548
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Sonakshi Sinha |
—
|
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: Sonakshi Sinha | Statement: [Lootera, castMember, Sonakshi Sinha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonakshi Sinha Context triple: [Lootera, castMember, Sonakshi Sinha]
-
A.
Sonakshi Sinha
chosen
Sonakshi Sinha is an Indian film actress best known for her work in Hindi cinema, including notable performances in both commercial blockbusters and critically acclaimed dramas.
-
B.
Neha Kapur
Neha Kapur is an Indian model, former Miss India Universe 2006, and fashion entrepreneur.
-
C.
Pooja Bhatt
Pooja Bhatt is an Indian actress, filmmaker, and producer known for her work in Hindi cinema since the early 1990s.
-
D.
Smriti Malhotra
Smriti Malhotra is an Indian politician, former television actress, and current Union Minister better known by her married name, Smriti Irani.
-
E.
Dishita Sehgal
Dishita Sehgal is an Indian child actress best known for her role in the critically acclaimed Bollywood film "Hindi Medium."
- 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_69e11e5010e48190ae1e9c9db9697637 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15a3320448190ae3931062599116e |
completed | April 29, 2026, 1:09 a.m. |
Created at: April 16, 2026, 8:47 p.m.