Triple

T2848504
Position Surface form Disambiguated ID Type / Status
Subject Ajay Banga E63036 entity
Predicate spouse P13 FINISHED
Object Ritu Banga E63036 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: Ritu Banga | Statement: [Ajay Banga, spouse, Ritu Banga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ritu Banga
Context triple: [Ajay Banga, spouse, Ritu Banga]
  • A. Ritu Banga chosen
    Ritu Banga is an Indian-American businesswoman and co-founder of the talent advisory firm Zoomdojo, known also as the wife of Mastercard executive and World Bank president Ajay Banga.
  • B. Jayati Ghosh
    Jayati Ghosh is an Indian development economist known for her work on globalization, gender, and economic policy, and for her influential role in academic and policy debates on inequality and development.
  • C. Madhabi Mukherjee
    Madhabi Mukherjee is a renowned Indian actress best known for her powerful performances in classic Bengali films, particularly in collaboration with director Satyajit Ray.
  • D. Labanya Das
    Labanya Das was the wife of renowned Bengali poet Jibanananda Das and a figure associated with his personal and literary life.
  • E. Ruma Bose
    Ruma Bose is an entrepreneur, investor, and author known for her leadership roles in social impact ventures and global business initiatives.
  • 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_69ab4c407c408190857d25e027155ce9 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdf403698819084fb4ace5839aa05 completed March 7, 2026, 8:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d81e76c8190aae5e6dd9b13e28b completed March 10, 2026, 1:32 p.m.
Created at: March 6, 2026, 10:02 p.m.