Triple
T12853944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Appa Sahib Bhonsle |
E307399
|
entity |
| Predicate | house |
P1505
|
FINISHED |
| Object | Bhonsle |
E59544
|
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: Bhonsle | Statement: [Appa Sahib Bhonsle, house, Bhonsle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bhonsle Context triple: [Appa Sahib Bhonsle, house, Bhonsle]
-
A.
Bhonsle
chosen
The Bhonsle were a prominent Maratha royal dynasty best known for producing Chhatrapati Shivaji, founder of the Maratha Empire in western India.
-
B.
Kulkarni
Kulkarni is a traditional village-level official in the Maratha administrative system responsible for maintaining land and revenue records.
-
C.
Sankhali
Sankhali is a village located in the North Goa district of the Indian state of Goa.
-
D.
Balkrishna
Balkrishna is an Indian architect renowned for his pioneering modernist designs and as the country’s first Pritzker Architecture Prize laureate.
-
E.
Parulkar
Parulkar was a notable Indian social worker and nationalist associated with the Servants of India Society, an organization dedicated to public service and social reform.
- 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_69d7bdf5e7cc8190be357278bc5ba3bb |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97021df7481909cd42a0f72040aa5 |
completed | April 10, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69ba79918819093e047ce22191923 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 9, 2026, 5:37 p.m.