Triple
T22229713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yash Chopra |
E549433
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Silsila |
—
|
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: Silsila | Statement: [Yash Chopra, notableWork, Silsila]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Silsila Context triple: [Yash Chopra, notableWork, Silsila]
-
A.
Silsila
chosen
Silsila is a 1981 Hindi romantic drama film directed by Yash Chopra, renowned for its exploration of extramarital relationships and its iconic cast including Amitabh Bachchan, Jaya Bachchan, and Rekha.
-
B.
Pakeezah
Pakeezah is a landmark 1972 Indian Hindi-language musical drama film celebrated for its poetic storytelling, iconic music, and Meena Kumari’s legendary performance.
-
C.
Dilwaala
Dilwaala is an Indian film best known for featuring actress Persis Khambatta in a notable role.
-
D.
Aži Dahāg
Aži Dahāg is a monstrous, many-headed dragon or serpent from ancient Iranian and Zoroastrian mythology, often depicted as a symbol of chaos and evil.
-
E.
Indeevar
Indeevar was a prominent Indian lyricist best known for his extensive and influential work in Hindi cinema songs.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf173308190a3d21bfc59b39728 |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:37 p.m.