Triple
T5778849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anupam Kher |
E127507
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Karma
"Karma" is a 1986 Indian Hindi-language action drama film directed by Subhash Ghai, known for its patriotic themes and ensemble cast including Anupam Kher, Dilip Kumar, and Anil Kapoor.
|
E546212
|
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: Karma | Statement: [Anupam Kher, notableWork, Karma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karma Context triple: [Anupam Kher, notableWork, Karma]
-
A.
Karma
"Karma" is a Grammy-winning R&B song by Alicia Keys, known for its soulful vocals and themes of romantic betrayal and retribution.
-
B.
Karma
Karma is an American singer and the daughter of rapper Ludacris, known for her appearances on reality television and social media presence.
-
C.
Carma
Carma is a fictional character appearing in the story "Cane."
-
D.
Karmi
Karmi is a Hebrew surname most notably associated with the Israeli architect Dov Karmi and his family of prominent architects.
-
E.
law of karma
The law of karma is a spiritual principle, central to Indian religions, that holds a person’s intentional actions inevitably shape their future experiences across this and possible future lives.
- 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: Karma Triple: [Anupam Kher, notableWork, Karma]
Generated description
"Karma" is a 1986 Indian Hindi-language action drama film directed by Subhash Ghai, known for its patriotic themes and ensemble cast including Anupam Kher, Dilip Kumar, and Anil Kapoor.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Karma Target entity description: "Karma" is a 1986 Indian Hindi-language action drama film directed by Subhash Ghai, known for its patriotic themes and ensemble cast including Anupam Kher, Dilip Kumar, and Anil Kapoor.
-
A.
Karma
"Karma" is a Grammy-winning R&B song by Alicia Keys, known for its soulful vocals and themes of romantic betrayal and retribution.
-
B.
Karma
Karma is an American singer and the daughter of rapper Ludacris, known for her appearances on reality television and social media presence.
-
C.
Carma
Carma is a fictional character appearing in the story "Cane."
-
D.
Karmi
Karmi is a Hebrew surname most notably associated with the Israeli architect Dov Karmi and his family of prominent architects.
-
E.
law of karma
The law of karma is a spiritual principle, central to Indian religions, that holds a person’s intentional actions inevitably shape their future experiences across this and possible future lives.
- 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_69c008361fa88190aefa4dc41b051e7f |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c029e107348190a03086f1cbfae0d3 |
completed | March 22, 2026, 5:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07e735f408190b188b94131f1e51b |
completed | March 22, 2026, 11:42 p.m. |
| NEDg | Description generation | batch_69c08dc00df48190ad2cf716ad6eeb87 |
completed | March 23, 2026, 12:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c08e3b05a881909892ce776309920d |
completed | March 23, 2026, 12:50 a.m. |
Created at: March 22, 2026, 3:50 p.m.