Triple
T21943980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maqbool |
E541889
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Piyush Mishra |
—
|
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: Piyush Mishra | Statement: [Maqbool, castMember, Piyush Mishra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piyush Mishra Context triple: [Maqbool, castMember, Piyush Mishra]
-
A.
Piyush Mishra
chosen
Piyush Mishra is an Indian actor, lyricist, singer, and theatre artist known for his intense performances and distinctive songwriting in Hindi cinema and theatre.
-
B.
Piyush Sharma
Piyush Sharma is a computer science researcher known for co-authoring the ALBERT language model paper in natural language processing.
-
C.
Piyush Kanojia
Piyush Kanojia is an Indian music composer best known for his work on the film "Gandhi, My Father."
-
D.
Rajeev Misra
Rajeev Misra is an Indian-born financier and executive best known for leading SoftBank’s Vision Fund, one of the world’s largest technology investment funds.
-
E.
Piyush Chawla
Piyush Chawla is an Indian leg-spin bowler who has represented India in international cricket and played extensively in the Indian Premier League.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1242515ec8190b015bf8c7b13be85 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:56 p.m.