Triple
T8549872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eighteen Greater Texts of Tamil |
E202418
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Sangam literature collection |
C9096
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Sangam literature collection Context triple: [Eighteen Greater Texts of Tamil, instanceOf, Sangam literature collection]
-
A.
Sanskrit literature
Sanskrit literature is the body of classical and post-classical writings in the Sanskrit language, encompassing religious scriptures, epic poetry, drama, philosophy, science, and aesthetics that shaped much of South Asian intellectual and cultural history.
-
B.
classical Tamil literature
chosen
Classical Tamil literature encompasses the ancient poetic, philosophical, and didactic works composed primarily between 300 BCE and 300 CE in Tamil, including the Sangam corpus and later ethical and devotional texts that shaped South Indian culture and thought.
-
C.
Persian poetry collection
A Persian poetry collection is an organized compilation of poems written in the Persian language, often unified by a common author, theme, period, or literary style.
-
D.
Indian literature
Indian literature encompasses the diverse body of written and oral works produced in the many languages of the Indian subcontinent, reflecting its rich cultural, religious, and historical traditions from ancient times to the present.
-
E.
Bengali poetry collection
A Bengali poetry collection is an anthology of poems written in the Bengali language, often reflecting the region’s cultural, emotional, and philosophical themes across various poets or a single poet’s body of work.
- F. None of above.
Provenance (1 batch)
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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
Created at: March 30, 2026, 6:19 p.m.