Triple
T17751007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamata Banerjee |
E443110
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Banerjee |
—
|
NE NERFINISHED |
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: Banerjee | Statement: [Mamata Banerjee, familyName, Banerjee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Banerjee Context triple: [Mamata Banerjee, familyName, Banerjee]
-
A.
Banerjee
chosen
Banerjee is a common Bengali surname in India, historically associated with the Brahmin community and prominent figures in politics, academia, and the arts.
-
B.
Abhijit Banerjee
Abhijit Banerjee is an Indian-American economist and Nobel laureate renowned for his experimental approach to alleviating global poverty.
-
C.
Abhijit Vinayak Banerjee
Abhijit Vinayak Banerjee is an Indian-American economist and Nobel laureate renowned for his experimental approach to alleviating global poverty.
-
D.
A. B. Bardhan
A. B. Bardhan was a prominent Indian communist politician who served as the longtime general secretary and key national leader of the Communist Party of India.
-
E.
Sendhil Mullainathan
Sendhil Mullainathan is an economist and professor known for his work in behavioral economics, development economics, and the application of data science and machine learning to social and economic problems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4841a401c8190ae1dc0ed7ae4cc26 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 10:10 a.m.