Triple
T23205027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jyotiba Temple |
E580427
|
entity |
| Predicate | hasDeity |
P5606
|
FINISHED |
| Object | Jyotiba |
—
|
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: Jyotiba | Statement: [Jyotiba Temple, hasDeity, Jyotiba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jyotiba Context triple: [Jyotiba Temple, hasDeity, Jyotiba]
-
A.
Jyotiba
chosen
Jyotiba is a Hindu deity, regarded as a form of Lord Shiva (often associated with Khandoba), venerated especially in Maharashtra.
-
B.
Bhimrao
Bhimrao is the given name of B. R. Ambedkar, the prominent Indian jurist, social reformer, and chief architect of the Indian Constitution.
-
C.
नाथूराम विनायक गोडसे
नाथूराम विनायक गोडसे वह भारतीय व्यक्ति था जिसने 1948 में महात्मा गांधी की हत्या की और जिसे इस राजनीतिक हत्या के लिए फांसी दी गई।
-
D.
Yamunabai Savarkar
Yamunabai Savarkar was the wife of Indian independence activist and Hindutva ideologue Vinayak Damodar Savarkar and a supportive figure in his political and social life.
-
E.
Sakharam Bapu
Sakharam Bapu was an influential 18th-century Maratha statesman and minister in the Peshwa administration of the Maratha Empire.
- 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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1907c1d7c8190aca252a39ae0da86 |
completed | April 29, 2026, 5 a.m. |
Created at: April 17, 2026, 4:07 p.m.