Triple
T16183533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fanaa |
E392742
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object |
Kunal Kohli
Kunal Kohli is an Indian film director, producer, and writer best known for his work in Hindi cinema, particularly romantic dramas.
|
E1203563
|
NE FINISHED |
How this triple was built (4 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 Kohli | Statement: [Fanaa, director, Kunal Kohli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kunal Kohli Context triple: [Fanaa, director, Kunal Kohli]
-
A.
Rahul Kohli
Rahul Kohli is a British actor known for his genre work in television and film, particularly in horror and supernatural projects.
-
B.
Pushmeet Kohli
Pushmeet Kohli is a computer scientist and AI researcher known for his work in deep learning and reinforcement learning at DeepMind, contributing to landmark systems such as AlphaGo Zero.
-
C.
Gautam Krishna
Gautam Krishna is the son of prominent Telugu film actor Mahesh Babu and is known primarily as a celebrity child in the Indian entertainment industry.
-
D.
Rohit Dhawan
Rohit Dhawan is an Indian film director known for directing Hindi-language commercial entertainers such as "Desi Boyz" and "Dishoom."
-
E.
Sachit Mehra
Sachit Mehra is a Canadian political figure who serves in a top leadership role within the Liberal Party of Canada.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kunal Kohli Triple: [Fanaa, director, Kunal Kohli]
Generated description
Kunal Kohli is an Indian film director, producer, and writer best known for his work in Hindi cinema, particularly romantic dramas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kunal Kohli Target entity description: Kunal Kohli is an Indian film director, producer, and writer best known for his work in Hindi cinema, particularly romantic dramas.
-
A.
Rahul Kohli
Rahul Kohli is a British actor known for his genre work in television and film, particularly in horror and supernatural projects.
-
B.
Pushmeet Kohli
Pushmeet Kohli is a computer scientist and AI researcher known for his work in deep learning and reinforcement learning at DeepMind, contributing to landmark systems such as AlphaGo Zero.
-
C.
Gautam Krishna
Gautam Krishna is the son of prominent Telugu film actor Mahesh Babu and is known primarily as a celebrity child in the Indian entertainment industry.
-
D.
Rohit Dhawan
Rohit Dhawan is an Indian film director known for directing Hindi-language commercial entertainers such as "Desi Boyz" and "Dishoom."
-
E.
Sachit Mehra
Sachit Mehra is a Canadian political figure who serves in a top leadership role within the Liberal Party of Canada.
- F. None of above. chosen
Provenance (5 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_6a0017a7223c81909f04144bdffb22ff |
completed | May 10, 2026, 5:29 a.m. |
| NEDg | Description generation | batch_6a00195984c881909483fbf2afb518d1 |
completed | May 10, 2026, 5:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0019cbdc64819092184420bd4fd8ed |
completed | May 10, 2026, 5:38 a.m. |
Created at: April 10, 2026, 5:02 a.m.