Triple
T20351565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aandhi |
E496023
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
J. Om Prakash
J. Om Prakash was a prominent Indian film producer and director known for his successful Hindi films from the 1960s through the 1980s.
|
E1438076
|
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: J. Om Prakash | Statement: [Aandhi, producer, J. Om Prakash]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: J. Om Prakash Context triple: [Aandhi, producer, J. Om Prakash]
-
A.
Pramod Kumar Mishra
Pramod Kumar Mishra is a senior Indian Administrative Service officer who serves as a key bureaucratic advisor and top aide to the Prime Minister of India.
-
B.
V. K. Singh
V. K. Singh is an Indian politician and retired four-star General of the Indian Army who has served as a Union minister in the Government of India.
-
C.
Ashok Mishra
Ashok Mishra is an Indian screenwriter known for his work on films such as "Welcome to Sajjanpur."
-
D.
S. K. Singh
S. K. Singh was an Indian civil servant and politician who served in various high-level administrative and gubernatorial roles.
-
E.
P. K. Mishra
P. K. Mishra is an Indian lyricist known for writing songs for Tamil cinema, including work on acclaimed film soundtracks.
- 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: J. Om Prakash Triple: [Aandhi, producer, J. Om Prakash]
Generated description
J. Om Prakash was a prominent Indian film producer and director known for his successful Hindi films from the 1960s through the 1980s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: J. Om Prakash Target entity description: J. Om Prakash was a prominent Indian film producer and director known for his successful Hindi films from the 1960s through the 1980s.
-
A.
Pramod Kumar Mishra
Pramod Kumar Mishra is a senior Indian Administrative Service officer who serves as a key bureaucratic advisor and top aide to the Prime Minister of India.
-
B.
V. K. Singh
V. K. Singh is an Indian politician and retired four-star General of the Indian Army who has served as a Union minister in the Government of India.
-
C.
Ashok Mishra
Ashok Mishra is an Indian screenwriter known for his work on films such as "Welcome to Sajjanpur."
-
D.
S. K. Singh
S. K. Singh was an Indian civil servant and politician who served in various high-level administrative and gubernatorial roles.
-
E.
P. K. Mishra
P. K. Mishra is an Indian lyricist known for writing songs for Tamil cinema, including work on acclaimed film soundtracks.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6784f8ff48190a070888786f6a989 |
completed | April 20, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08acc90ddc8190a78c414350feeae6 |
completed | May 16, 2026, 5:43 p.m. |
| NEDg | Description generation | batch_6a08add512548190a900997f6b4126e7 |
completed | May 16, 2026, 5:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08ae3414388190bd5cf3cfce098d0c |
completed | May 16, 2026, 5:49 p.m. |
Created at: April 16, 2026, 11:24 a.m.