Triple
T16527846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mani Kaul |
E401485
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Siddheshwari |
E1218709
|
NE FINISHED |
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: Siddheshwari | Statement: [Mani Kaul, directed, Siddheshwari]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Siddheshwari Context triple: [Mani Kaul, directed, Siddheshwari]
-
A.
Siddheshwari
chosen
Siddheshwari is an Indian art-house documentary film by Mani Kaul that poetically explores the life and music of classical singer Siddheshwari Devi.
-
B.
Mallishwari
Mallishwari is a 2004 Telugu romantic comedy film starring Venkatesh and Katrina Kaif, noted for its entertaining blend of humor, romance, and music.
-
C.
Maheshwari
Maheshwari is a Hindu goddess form of Mahadevi, revered as a supreme mother deity and embodiment of divine feminine power.
-
D.
Gauri
Gauri is a central character in Jhumpa Lahiri’s novel "The Lowland," whose life is shaped by political upheaval, personal loss, and the complexities of migration and identity.
-
E.
Gauri
Gauri is a revered Hindu goddess associated with purity, marital bliss, and fertility, often identified as a form of Parvati, the consort of Lord Shiva.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed57be481908625d4c5aab0940c |
completed | April 18, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0067a7616c8190af486bef3331e115 |
completed | May 10, 2026, 11:10 a.m. |
Created at: April 10, 2026, 5:14 a.m.