Triple
T22292484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | V. Shantaram |
E551030
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sandhya |
—
|
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: Sandhya | Statement: [V. Shantaram, spouse, Sandhya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandhya Context triple: [V. Shantaram, spouse, Sandhya]
-
A.
Sandhya
Sandhya was an Indian actress and the mother of former Tamil Nadu Chief Minister and film star J. Jayalalithaa.
-
B.
Sandhya
chosen
Sandhya is an Indian actress best known for her leading role in the film "Pinjra."
-
C.
Subha
Subha is the given first name of British television presenter and journalist Naga Munchetty.
-
D.
Ishana
Ishana is a Hindu deity associated with the northeast direction and often regarded as a form or aspect of Shiva within the group of directional guardians.
-
E.
Shubi
Shubi is a Bantu language spoken by the Shubi people of northwestern Tanzania, closely related to other Rwanda-Rundi languages.
- 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_69e11e45fb848190a1b2ae21296e3a5f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1560d1ec48190ab86f158c94b677b |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 16, 2026, 8:41 p.m.