Triple
T8565026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mani Ratnam |
E202781
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Raavanan |
E741425
|
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: Raavanan | Statement: [Mani Ratnam, notableWork, Raavanan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raavanan Context triple: [Mani Ratnam, notableWork, Raavanan]
-
A.
Raavanan
chosen
Raavanan is a 2010 Tamil-language psychological action thriller film directed by Mani Ratnam, in which Vikram plays a complex outlaw inspired by the epic character Ravana.
-
B.
Dasavathaaram
Dasavathaaram is a 2008 Indian Tamil science-fiction action film famed for Kamal Haasan’s portrayal of ten distinct roles and its complex, time-spanning narrative.
-
C.
Rangasthalam
Rangasthalam is a critically acclaimed Telugu-language period action drama film known for its rustic village setting, powerful performances, and direction by Sukumar.
-
D.
Vetrimaaran
Vetrimaaran is an acclaimed Indian filmmaker and screenwriter known for his gritty, realistic Tamil-language films and multiple National Film Awards.
-
E.
Kabali
Kabali is a 2016 Indian Tamil-language action drama film starring Rajinikanth as an aging gangster seeking revenge and redemption.
- 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_69ca8327b0a881908606ff860713964d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9d2331881909d92ddde90f580e9 |
completed | March 31, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce89677888819091dfda14ce6baef3 |
completed | April 2, 2026, 3:21 p.m. |
Created at: March 30, 2026, 6:20 p.m.