Triple
T203948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Partha Dasgupta |
E4568
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Partha
Partha is a given name commonly used in India, often associated with figures in academia, arts, and public life.
|
E26020
|
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: Partha | Statement: [Partha Dasgupta, givenName, Partha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Partha Context triple: [Partha Dasgupta, givenName, Partha]
-
A.
Nathuram
Nathuram was the Indian nationalist and Hindu extremist who assassinated Mahatma Gandhi in 1948.
-
B.
Neal Mohan
Neal Mohan is an Indian-American technology executive and digital advertising expert who serves as the CEO of YouTube.
-
C.
Eknath
Eknath was a prominent 16th-century Marathi saint-poet and scholar known for his devotional literature and contributions to the Bhakti movement in Maharashtra.
-
D.
Mahadev Desai
Mahadev Desai was an Indian independence activist, writer, and close associate and secretary of Mahatma Gandhi, known for translating Gandhi’s autobiography into English and documenting the freedom struggle.
-
E.
Navjivan
Navjivan was an Indian publishing house and imprint associated with Mahatma Gandhi, known for issuing many of his writings and related works on the Indian independence movement.
- 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: Partha Triple: [Partha Dasgupta, givenName, Partha]
Generated description
Partha is a given name commonly used in India, often associated with figures in academia, arts, and public life.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Partha Target entity description: Partha is a given name commonly used in India, often associated with figures in academia, arts, and public life.
-
A.
Nathuram
Nathuram was the Indian nationalist and Hindu extremist who assassinated Mahatma Gandhi in 1948.
-
B.
Neal Mohan
Neal Mohan is an Indian-American technology executive and digital advertising expert who serves as the CEO of YouTube.
-
C.
Eknath
Eknath was a prominent 16th-century Marathi saint-poet and scholar known for his devotional literature and contributions to the Bhakti movement in Maharashtra.
-
D.
Mahadev Desai
Mahadev Desai was an Indian independence activist, writer, and close associate and secretary of Mahatma Gandhi, known for translating Gandhi’s autobiography into English and documenting the freedom struggle.
-
E.
Navjivan
Navjivan was an Indian publishing house and imprint associated with Mahatma Gandhi, known for issuing many of his writings and related works on the Indian independence movement.
- 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_69a25737567c81908f9c505300239181 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25be898ec8190b5e752a1d3b6f466 |
completed | Feb. 28, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a328150c008190a01abaf26bdaab84 |
completed | Feb. 28, 2026, 5:38 p.m. |
| NEDg | Description generation | batch_69a328d5ace8819095df251af6a964b8 |
completed | Feb. 28, 2026, 5:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a3293e606881909cec2888093ec079 |
completed | Feb. 28, 2026, 5:43 p.m. |
Created at: Feb. 28, 2026, 2:51 a.m.