Triple
T18693153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lavani dancers |
E457048
|
entity |
| Predicate | relatedArtForm |
P37
|
FINISHED |
| Object | Tamasha |
—
|
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: Tamasha | Statement: [Lavani dancers, relatedArtForm, Tamasha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamasha Context triple: [Lavani dancers, relatedArtForm, Tamasha]
-
A.
Tamasha
chosen
Tamasha is a traditional Marathi folk theatre form from Maharashtra, India, known for its lively blend of music, dance, and dramatic performance.
-
B.
Hungama
"Hungama" is a 2003 Indian Hindi-language comedy film directed by Priyadarshan, known for its ensemble cast and farcical plot centered on misunderstandings and mistaken identities.
-
C.
Mardaani
Mardaani is a 2014 Indian crime thriller film that follows a tough female police officer’s pursuit of a child trafficking racket.
-
D.
Bhagam Bhag
Bhagam Bhag is a 2006 Indian Hindi-language comedy film directed by Priyadarshan, known for its slapstick humor and ensemble cast including Akshay Kumar, Govinda, and Lara Dutta.
-
E.
Kabzaa
Kabzaa is a 1992 Hindi-language action crime film known for its underworld-centric storyline and ensemble cast, including Paresh Rawal.
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e562e581f48190997d279296a31e7f |
completed | April 19, 2026, 11:19 p.m. |
Created at: April 10, 2026, 11:49 a.m.