Triple
T16272747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dil Chahta Hai |
E395041
|
entity |
| Predicate | leadActress |
P6108
|
FINISHED |
| Object | Sonali Kulkarni |
E584538
|
NE FINISHED |
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: Sonali Kulkarni | Statement: [Dil Chahta Hai, leadActress, Sonali Kulkarni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonali Kulkarni Context triple: [Dil Chahta Hai, leadActress, Sonali Kulkarni]
-
A.
Sonali Kulkarni
chosen
Sonali Kulkarni is an acclaimed Indian actress known for her versatile performances across Marathi and Hindi cinema, as well as in international films.
-
B.
Kavita Rao
Kavita Rao is a fictional geneticist in the X-Men universe known for developing a controversial "cure" for mutant powers.
-
C.
Bhavna Vaswani
Bhavna Vaswani is a psychologist and social worker best known as the wife of filmmaker M. Night Shyamalan and for her involvement in philanthropic and charitable initiatives.
-
D.
Shibani Santurkar
Shibani Santurkar is a computer scientist and AI researcher known for her work on machine learning robustness and safety, and as a co-founder of the AI safety company Anthropic.
-
E.
Devi Parikh
Devi Parikh is a computer vision and AI researcher known for her work on visual question answering, human-AI collaboration, and interpretable machine learning.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2460b22d88190bdc7cf509cf74198 |
completed | April 17, 2026, 2:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007d9a8d7481908c7bc4711ddacc13 |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 10, 2026, 5:05 a.m.