Triple
T21428689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krantiveer |
E528626
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object |
K. K. Singh
K. K. Singh is an Indian screenwriter best known for his work on the socially charged Bollywood film "Krantiveer."
|
E1490081
|
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: K. K. Singh | Statement: [Krantiveer, writer, K. K. Singh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K. K. Singh Context triple: [Krantiveer, writer, K. K. Singh]
-
A.
R. K. Singh
R. K. Singh is an Indian politician and former bureaucrat who serves as a Member of Parliament and has held ministerial positions in the Government of India.
-
B.
Shivpal Singh Yadav
Shivpal Singh Yadav is an Indian politician from Uttar Pradesh, known for his long association with the Samajwadi Party and for holding several key ministerial and organizational roles in state politics.
-
C.
Tirath Singh Thakur
Tirath Singh Thakur is an Indian jurist who served as the 43rd Chief Justice of India.
-
D.
Vijay Kumar Choudhary
Vijay Kumar Choudhary is an Indian politician from Bihar who has held key ministerial portfolios in the state government, including finance.
-
E.
Veerendra Saxena
Veerendra Saxena is an Indian actor known for his character roles in Hindi films and television.
- 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: K. K. Singh Triple: [Krantiveer, writer, K. K. Singh]
Generated description
K. K. Singh is an Indian screenwriter best known for his work on the socially charged Bollywood film "Krantiveer."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: K. K. Singh Target entity description: K. K. Singh is an Indian screenwriter best known for his work on the socially charged Bollywood film "Krantiveer."
-
A.
R. K. Singh
R. K. Singh is an Indian politician and former bureaucrat who serves as a Member of Parliament and has held ministerial positions in the Government of India.
-
B.
Shivpal Singh Yadav
Shivpal Singh Yadav is an Indian politician from Uttar Pradesh, known for his long association with the Samajwadi Party and for holding several key ministerial and organizational roles in state politics.
-
C.
Tirath Singh Thakur
Tirath Singh Thakur is an Indian jurist who served as the 43rd Chief Justice of India.
-
D.
Vijay Kumar Choudhary
Vijay Kumar Choudhary is an Indian politician from Bihar who has held key ministerial portfolios in the state government, including finance.
-
E.
Veerendra Saxena
Veerendra Saxena is an Indian actor known for his character roles in Hindi films and television.
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee813db52c8190ac933bc6ec4dbf77 |
completed | April 26, 2026, 9:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09eecc2a408190a923b8455e2617d7 |
completed | May 17, 2026, 4:37 p.m. |
| NEDg | Description generation | batch_6a09efc6a57c81908c72e794c16989d4 |
completed | May 17, 2026, 4:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09f07a090c8190aead09c3b06e0e34 |
completed | May 17, 2026, 4:44 p.m. |
Created at: April 16, 2026, 5:49 p.m.