Triple
T21110305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amrish Puri |
E520153
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Damini |
—
|
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: Damini | Statement: [Amrish Puri, notableWork, Damini]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Damini Context triple: [Amrish Puri, notableWork, Damini]
-
A.
Damini
chosen
Damini is a critically acclaimed 1993 Indian Hindi-language courtroom drama film directed by Rajkumar Santoshi, known for its powerful portrayal of a woman's fight for justice.
-
B.
Nandini
Nandini is a divine cow in Hindu mythology, famed as a wish-fulfilling offspring of the celestial cow Kamadhenu.
-
C.
Aradhana
Aradhana is a landmark 1969 Hindi romantic drama film, celebrated for its music and performances, that significantly boosted the stardom of its lead actors.
-
D.
Naina
Naina is a feminine given name commonly used in various cultures, including Russian and South Asian contexts.
-
E.
Meenakshi
Meenakshi is a revered form of the Hindu goddess Parvati, worshipped especially in South India as the fish-eyed consort of Shiva and patron deity of Madurai.
- 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_69e0b509a318819092fbbcb21d1fe603 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72101f7308190beb202a052ff04d2 |
completed | April 21, 2026, 7:02 a.m. |
Created at: April 16, 2026, 2:54 p.m.