Triple

T3192102
Position Surface form Disambiguated ID Type / Status
Subject Citigroup E66845 entity
Predicate hasBrand P1500 FINISHED
Object Citi E220765 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: Citi | Statement: [Citigroup, hasBrand, Citi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Citi
Context triple: [Citigroup, hasBrand, Citi]
  • A. Citibank chosen
    Citibank is a major global banking and financial services institution headquartered in the United States, known for its extensive international retail and corporate banking operations.
  • B. Chase Bank
    Chase Bank is a major U.S. consumer and commercial banking institution operated by JPMorgan Chase, offering a wide range of financial products and services nationwide.
  • C. Bank of America
    Bank of America is one of the largest multinational banking and financial services corporations in the United States, offering a wide range of consumer, corporate, and investment banking products globally.
  • D. Wells Fargo
    Wells Fargo is a large American multinational financial services company and one of the biggest banks in the United States.
  • E. Comerica Bank
    Comerica Bank is a large U.S. financial services company headquartered in Dallas, Texas, known for its commercial banking, wealth management, and retail banking operations.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6e8e4b48190bc7c6443fc6da900 completed March 8, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3608e261081908b0633bf11ea655b completed March 13, 2026, 12:55 a.m.
Created at: March 8, 2026, 3:07 p.m.