Triple
T21428369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gardish |
E528619
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Mukesh Rishi |
—
|
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: Mukesh Rishi | Statement: [Gardish, starring, Mukesh Rishi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mukesh Rishi Context triple: [Gardish, starring, Mukesh Rishi]
-
A.
Mukesh Rishi
chosen
Mukesh Rishi is an Indian actor best known for his powerful villainous and character roles in Hindi and regional cinema.
-
B.
Rishi Bhat
Rishi Bhat is an actor best known for his role in the family fantasy film "The Indian in the Cupboard."
-
C.
Shiv Kumar
Shiv Kumar was a renowned Punjabi poet celebrated for his deeply emotional and romantic verse, which left a lasting impact on modern Punjabi literature.
-
D.
Mukesh Chhabra
Mukesh Chhabra is an Indian casting director and filmmaker known for his work on numerous prominent Bollywood films.
-
E.
Sanjay Sankla
Sanjay Sankla is an Indian film editor known for his work on Hindi cinema, including the popular film "Hum Hain Rahi Pyar Ke."
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b3e74bcc81909ad66e3c59152ffc |
completed | April 22, 2026, 11:41 a.m. |
Created at: April 16, 2026, 5:49 p.m.