Triple
T21772902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Renuka |
E537479
|
entity |
| Predicate | alias |
P39
|
FINISHED |
| Object | Renuka Devi |
—
|
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: Renuka Devi | Statement: [Renuka, alias, Renuka Devi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Renuka Devi Context triple: [Renuka, alias, Renuka Devi]
-
A.
Renuka Devi
chosen
Renuka Devi is known as the wife of Indian politician and Marumalarchi Dravida Munnetra Kazhagam (MDMK) leader Vaiko.
-
B.
Bhuvaneshwari Devi
Bhuvaneshwari Devi was an Indian woman best known as the mother of Swami Vivekananda (Narendranath Datta), one of modern India's most influential spiritual leaders.
-
C.
Neila Devi
Neila Devi is the widow of legendary Indian actor Shammi Kapoor, known for her association with one of Hindi cinema’s most iconic stars.
-
D.
Padma Devi
Padma Devi was an Indian actress known for her roles in classic Bengali cinema, particularly in mid-20th-century films.
-
E.
Harsiddhi Devi
Harsiddhi Devi is a revered Hindu goddess, considered a powerful form of Shakti and widely worshipped in western India, especially in Gujarat and Madhya Pradesh.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031af6a488190a2dcebed43d199d4 |
completed | April 28, 2026, 4:03 a.m. |
Created at: April 16, 2026, 6:51 p.m.