Triple

T13807689
Position Surface form Disambiguated ID Type / Status
Subject Gerald Loeb Award E331802 entity
Predicate founder P104 FINISHED
Object Gerald Loeb E1062760 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: Gerald Loeb | Statement: [Gerald Loeb Award, founder, Gerald Loeb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gerald Loeb
Context triple: [Gerald Loeb Award, founder, Gerald Loeb]
  • A. Gerald Loeb chosen
    Gerald Loeb was a prominent American stockbroker, financial writer, and co-founder of E.F. Hutton, renowned for his influential investment advice and market commentary.
  • B. Alfred E. Kahn
    Alfred E. Kahn was an American economist and regulator best known as the chief architect of U.S. airline deregulation in the late 1970s.
  • C. Solomon Loeb
    Solomon Loeb was a prominent 19th-century German-American banker and co-founder of the influential investment bank Kuhn, Loeb & Co.
  • D. Irving Glassberg
    Irving Glassberg was a Polish-born American cinematographer known for his work on numerous Universal Pictures films in the 1940s and 1950s.
  • E. Edgar M. Kahn
    Edgar M. Kahn was an American neurosurgeon and academic known for his contributions to the development of neurosurgical techniques and education in the mid-20th century.
  • 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_69d81c59f8808190a851bc56afdc55e9 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de026eae8481908b8880635e6a9152 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8dc1ec0819098c4f32eb3991613 completed May 3, 2026, 9:06 p.m.
Created at: April 9, 2026, 10:12 p.m.