Triple
T21944434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billu |
E541899
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Lara Dutta |
—
|
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: Lara Dutta | Statement: [Billu, starring, Lara Dutta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lara Dutta Context triple: [Billu, starring, Lara Dutta]
-
A.
Lara Dutta
chosen
Lara Dutta is an Indian actress, model, and former Miss Universe (2000) known for her work in Bollywood films.
-
B.
Priya Dutt
Priya Dutt is an Indian politician and former Member of Parliament from Mumbai, known for her work with the Indian National Congress and as the daughter of actors-turned-politicians Sunil Dutt and Nargis.
-
C.
Divya Dutta
Divya Dutta is an Indian film actress known for her versatile supporting and character roles across Hindi and Punjabi cinema.
-
D.
Radhika Roy
Radhika Roy is an Indian media executive and co-founder of the news network NDTV.
-
E.
Radhika Khanna
Radhika Khanna is known as the sister of Indian-American celebrity chef and restaurateur Vikas Khanna.
- 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.