Triple

T22599257
Position Surface form Disambiguated ID Type / Status
Subject Deewani Mastani E574767 entity
Predicate productionCompany P490 FINISHED
Object Eros International 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: Eros International | Statement: [Deewani Mastani, productionCompany, Eros International]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eros International
Context triple: [Deewani Mastani, productionCompany, Eros International]
  • A. Eros International chosen
    Eros International is a major Indian film production and distribution company known for financing and releasing numerous prominent Bollywood and regional movies worldwide.
  • B. ITC Entertainment
    ITC Entertainment was a British television production and distribution company best known for creating and financing popular TV series and films from the 1960s through the 1980s.
  • C. Wadia Group
    Wadia Group is one of India’s oldest conglomerates, with diversified interests spanning textiles, aviation, real estate, food, and chemicals.
  • D. Regal Entertainment Group
    Regal Entertainment Group is one of the largest movie theater chains in the United States, operating multiplex cinemas across the country.
  • E. Ramoji Group
    Ramoji Group is an Indian conglomerate best known for its diversified interests in media, entertainment, and hospitality.
  • 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_69e245bc11308190b69d794d5d1e0bb6 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1626b5f5481909a104088d1c96720 completed April 29, 2026, 1:44 a.m.
Created at: April 17, 2026, 2:50 p.m.