Triple
T8738985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaaka Muttai |
E207455
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
Wunderbar Films
Wunderbar Films is an Indian film production company, founded by actor Dhanush, known for producing acclaimed Tamil-language movies.
|
E754857
|
NE FINISHED |
How this triple was built (4 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: Wunderbar Films | Statement: [Kaaka Muttai, productionCompany, Wunderbar Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wunderbar Films Context triple: [Kaaka Muttai, productionCompany, Wunderbar Films]
-
A.
Bavaria Film
Bavaria Film is a major German film production and studio company known for producing numerous acclaimed movies and television series.
-
B.
Allegro Films
Allegro Films is a film production company known for producing feature films such as the 1997 movie "Trucks."
-
C.
Elzévir Films
Elzévir Films is a French film production company known for producing independent and auteur-driven cinema.
-
D.
Constantin Film
Constantin Film is a German film production and distribution company known for producing a wide range of international films, including major genre franchises.
-
E.
Minerva Film
Minerva Film is an Italian film distribution and production company known for handling classic and auteur cinema releases.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Wunderbar Films Triple: [Kaaka Muttai, productionCompany, Wunderbar Films]
Generated description
Wunderbar Films is an Indian film production company, founded by actor Dhanush, known for producing acclaimed Tamil-language movies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wunderbar Films Target entity description: Wunderbar Films is an Indian film production company, founded by actor Dhanush, known for producing acclaimed Tamil-language movies.
-
A.
Bavaria Film
Bavaria Film is a major German film production and studio company known for producing numerous acclaimed movies and television series.
-
B.
Allegro Films
Allegro Films is a film production company known for producing feature films such as the 1997 movie "Trucks."
-
C.
Elzévir Films
Elzévir Films is a French film production company known for producing independent and auteur-driven cinema.
-
D.
Constantin Film
Constantin Film is a German film production and distribution company known for producing a wide range of international films, including major genre franchises.
-
E.
Minerva Film
Minerva Film is an Italian film distribution and production company known for handling classic and auteur cinema releases.
- F. None of above. chosen
Provenance (5 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_69ca835a03a081909d4d4cd01a18c9fb |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d470c8c81909ead395ef704c6ba |
completed | March 31, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf42d5dd508190854fbbc2541aa819 |
completed | April 3, 2026, 4:32 a.m. |
| NEDg | Description generation | batch_69cf440051bc8190ad9d649150187932 |
completed | April 3, 2026, 4:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cf4473ee0081908ed22eb0d855d7dd |
completed | April 3, 2026, 4:39 a.m. |
Created at: March 30, 2026, 6:38 p.m.