Triple
T3848464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Man Singh |
E85230
|
entity |
| Predicate | closeAssociateOf |
P2830
|
FINISHED |
| Object | Nana Sahib |
E13286
|
NE FINISHED |
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: Nana Sahib | Statement: [Man Singh, closeAssociateOf, Nana Sahib]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nana Sahib Context triple: [Man Singh, closeAssociateOf, Nana Sahib]
-
A.
Nana Sahib
chosen
Nana Sahib was a prominent Indian aristocrat and leader who played a key role in directing rebel forces against British rule during the Indian Rebellion of 1857.
-
B.
Harkha Bai
Harkha Bai, better known by her royal title Mariam-uz-Zamani, was a Rajput princess who became a prominent Mughal empress as the wife of Emperor Akbar and mother of Jahangir.
-
C.
Laxmibai
Laxmibai was the wife of the renowned Kannada poet and Jnanpith awardee D. R. Bendre.
-
D.
Lal Bai
Lal Bai was the mother of Bahadur Shah II, the last Mughal emperor of India.
-
E.
Gopikabai
Gopikabai was the wife of Peshwa Balaji Baji Rao and a prominent Maratha noblewoman known for her influence in 18th-century Maratha politics.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69aed936de1c81908f91bed80f70abb2 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeebcc8a0481909c35161336bdfbf9 |
completed | March 9, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51c788a088190aa91261b83f21d86 |
completed | March 14, 2026, 8:29 a.m. |
Created at: March 9, 2026, 3:19 p.m.