Triple
T16183494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarfarosh |
E392741
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Pradeep Rawat |
E850375
|
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: Pradeep Rawat | Statement: [Sarfarosh, starring, Pradeep Rawat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pradeep Rawat Context triple: [Sarfarosh, starring, Pradeep Rawat]
-
A.
Pradeep Rawat
chosen
Pradeep Rawat is an Indian actor best known for his villainous roles in films such as "Ghajini" and for character parts in major Hindi and regional cinema.
-
B.
Vijay Maurya
Vijay Maurya is an Indian actor, writer, and director known for his work in Hindi cinema and web series.
-
C.
Raghuveer Chaudhari
Raghuveer Chaudhari is an acclaimed Indian Gujarati writer and scholar renowned for his influential novels, poetry, and literary criticism.
-
D.
Naresh Kumar
Naresh Kumar is a senior Indian Administrative Service (IAS) officer who has served in top bureaucratic positions in the Government of Delhi.
-
E.
Vipin Sharma
Vipin Sharma is an Indian actor known for his character roles in Hindi cinema and streaming projects, including a prominent part in the action thriller film "Monkey Man."
- 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_69d87f1e49ac8190a311b54d32990576 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2205ef39081908da383abdebc2ccc |
completed | April 17, 2026, 11:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0025f183d88190b269233ff6e65d75 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:02 a.m.