Triple

T23065596
Position Surface form Disambiguated ID Type / Status
Subject Harold Blum E575030 entity
Predicate hasSurname P18 FINISHED
Object Blum 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: Blum | Statement: [Harold Blum, hasSurname, Blum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blum
Context triple: [Harold Blum, hasSurname, Blum]
  • A. Blum chosen
    Blum is a surname of German and Jewish origin borne by various notable individuals across fields such as mathematics, politics, and the arts.
  • B. Bluhm
    Bluhm is a surname most notably associated with Norman Bluhm, an American abstract expressionist painter.
  • C. Blumhardt
    Blumhardt is a surname most notably associated with Maureen Blumhardt, an American former model and philanthropist known as the wife of basketball Hall of Famer Charles Barkley.
  • D. Blu
    Blu is a popular electronic cigarette and vaping brand known for its range of rechargeable and disposable e-cigarette products.
  • E. Blu
    Blu is a domesticated Spix's macaw who serves as the timid yet brave protagonist of the animated Rio film series.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f189a3e39481909cad356ad0bb3ee6 completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.