Triple
T17818366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rajaram Bhonsle |
E444906
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Soyarabai |
—
|
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: Soyarabai | Statement: [Rajaram Bhonsle, mother, Soyarabai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soyarabai Context triple: [Rajaram Bhonsle, mother, Soyarabai]
-
A.
Soyarabai
chosen
Soyarabai was a Maratha queen and consort of Chhatrapati Shivaji Maharaj, known as the mother of Rajaram I and a key figure in the politics of the early Maratha Empire.
-
B.
Sojitra
Sojitra is a town in the Anand district of Gujarat, India, known for its agricultural surroundings and local dairy-based economy.
-
C.
Sabya
Sabya is a city in southwestern Saudi Arabia located within the Jazan Region near the Red Sea coast.
-
D.
Shoba
Shoba was an acclaimed Indian film actress known for her powerful performances in Malayalam and Tamil cinema, whose promising career was cut short by her tragic death at a young age.
-
E.
Orya
Orya is the ISO 15924 script code representing the Odia script used for writing the Odia language of eastern India.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e488812df081909771d51c54c405fe |
completed | April 19, 2026, 7:47 a.m. |
Created at: April 10, 2026, 10:14 a.m.