Triple

T18985618
Position Surface form Disambiguated ID Type / Status
Subject George Schwab E464548 entity
Predicate familyName P18 FINISHED
Object Schwab 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: Schwab | Statement: [George Schwab, familyName, Schwab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Schwab
Context triple: [George Schwab, familyName, Schwab]
  • A. Schwab chosen
    Schwab is a German-language surname borne by numerous notable individuals in fields such as business, academia, and the arts.
  • B. Charles Schwab Corporation
    Charles Schwab Corporation is a major American financial services company best known for its discount brokerage, wealth management, and banking services.
  • C. Merrill Lynch
    Merrill Lynch is a major American wealth management and investment banking firm known for its brokerage services and role in global financial markets.
  • D. Fidelity Investments
    Fidelity Investments is a major American multinational financial services corporation best known for its mutual funds, brokerage services, and retirement investment products.
  • E. State Street Corporation
    State Street Corporation is a major American financial services and bank holding company specializing in investment servicing, investment management, and asset management for institutional investors worldwide.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d65f7f08819088f56e8e030851b1 completed April 20, 2026, 7:31 a.m.
Created at: April 10, 2026, 12:01 p.m.