Triple

T8565129
Position Surface form Disambiguated ID Type / Status
Subject Balu Mahendra E202783 entity
Predicate notableWork P4 FINISHED
Object Sadma E743344 NE FINISHED

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: Sadma | Statement: [Balu Mahendra, notableWork, Sadma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sadma
Context triple: [Balu Mahendra, notableWork, Sadma]
  • A. Sadma chosen
    Sadma is a critically acclaimed 1983 Indian drama film, directed by Balu Mahendra and celebrated for Sridevi’s iconic performance as a woman suffering from retrograde amnesia.
  • B. Sarfarosh
    Sarfarosh is a 1999 Indian Hindi-language action drama film acclaimed for its gritty portrayal of cross-border terrorism and for featuring Aamir Khan in a powerful lead role as an honest police officer.
  • C. Sarahama
    Sarahama is a small coastal settlement on Irabu Island in Okinawa Prefecture, Japan, known for its traditional island community and proximity to scenic beaches and coral reefs.
  • D. Dhaman
    Dhaman is a regional Arab multilateral institution that promotes and guarantees investment and trade in Arab countries by providing political and commercial risk insurance and related services.
  • E. Tareeno
    Tareeno is an alternative name for Wanetsi, an Eastern Iranian language closely related to Pashto and spoken primarily in parts of Pakistan and Afghanistan.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca8327b0a881908606ff860713964d completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe9d2331881909d92ddde90f580e9 completed March 31, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea87badf081909727808f0e14ae45 completed April 2, 2026, 5:33 p.m.
Created at: March 30, 2026, 6:20 p.m.