Triple
T21428366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gardish |
E528619
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Amrish Puri |
—
|
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: Amrish Puri | Statement: [Gardish, starring, Amrish Puri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amrish Puri Context triple: [Gardish, starring, Amrish Puri]
-
A.
Amrish Puri
chosen
Amrish Puri was a renowned Indian actor best known for his powerful villainous roles in Hindi cinema and for playing the iconic antagonist Mola Ram in the film "Indiana Jones and the Temple of Doom."
-
B.
Sooraj Pancholi
Sooraj Pancholi is an Indian film actor known for his Bollywood debut in the romantic action film "Hero" (2015) and for being the son of actors Aditya Pancholi and Zarina Wahab.
-
C.
Paresh Rawal
Paresh Rawal is a renowned Indian actor and comedian celebrated for his versatile performances in Hindi cinema and theatre.
-
D.
Vijay Raaz
Vijay Raaz is an Indian actor known for his distinctive voice and comic character roles in Hindi cinema.
-
E.
Amit Phalke
Amit Phalke is an actor known for his role in the Indian film "Mammo."
- 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.