Triple

T12946372
Position Surface form Disambiguated ID Type / Status
Subject Manvinder Singh Banga E309776 entity
Predicate relative P37 FINISHED
Object Ajay Banga E10452 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: Ajay Banga | Statement: [Manvinder Singh Banga, relative, Ajay Banga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ajay Banga
Context triple: [Manvinder Singh Banga, relative, Ajay Banga]
  • A. Ajay Banga chosen
    Ajay Banga is an Indian-American business executive and former Mastercard CEO who became president of the World Bank, focusing on global development and climate-related challenges.
  • B. Sanjiv Banga
    Sanjiv Banga is an individual notable enough to be recognized as a prominent bearer of the surname Banga.
  • C. Vikram Pandit
    Vikram Pandit is an Indian-American banker best known for serving as the CEO of Citigroup during the global financial crisis.
  • D. Nusli Wadia
    Nusli Wadia is an Indian industrialist and chairman of the Wadia Group, known for leading major companies such as Bombay Dyeing and Britannia Industries.
  • E. Navin Chowdhry
    Navin Chowdhry is a British actor known for his work in television, film, and theatre, including prominent roles in UK comedy and drama series.
  • 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_69d7bdfb57a88190836b743e2825feca completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97e1b3694819098527dcea3cfed93 completed April 10, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8d9669c819090471eb7e035d83d completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 5:43 p.m.