Triple
T4521846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trolls (film) |
E103286
|
entity |
| Predicate | voiceActor |
P1507
|
FINISHED |
| Object | Kunal Nayyar |
E193357
|
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: Kunal Nayyar | Statement: [Trolls (film), voiceActor, Kunal Nayyar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kunal Nayyar Context triple: [Trolls (film), voiceActor, Kunal Nayyar]
-
A.
Kunal Nayyar
chosen
Kunal Nayyar is a British-Indian actor best known for playing the socially awkward astrophysicist Rajesh Koothrappali on the hit sitcom "The Big Bang Theory."
-
B.
Anurag Behar
Anurag Behar is an Indian educationist and social sector leader best known for heading the Azim Premji Foundation and contributing to large-scale education reform in India.
-
C.
Sanjay Kapoor
Sanjay Kapoor is an Indian film and television actor and producer known for his work in Hindi cinema since the 1990s.
-
D.
Somesh Jha
Somesh Jha is a computer scientist known for his research in formal methods, security, and software verification.
-
E.
Rajkummar Rao
Rajkummar Rao is an acclaimed Indian film actor known for his versatile performances in Hindi cinema, particularly in critically praised independent and mainstream films.
- 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd574bd6908190b939d92b5809b101 |
completed | March 20, 2026, 2:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bda43a82c08190b3d43efcee45a8ea |
completed | March 20, 2026, 7:47 p.m. |
Created at: March 20, 2026, 1:02 p.m.