Triple

T11818818
Position Surface form Disambiguated ID Type / Status
Subject Serpico E281071 entity
Predicate basedOnAuthor P2806 FINISHED
Object Peter Maas E489032 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: Peter Maas | Statement: [Serpico, basedOnAuthor, Peter Maas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Maas
Context triple: [Serpico, basedOnAuthor, Peter Maas]
  • A. Peter Maas chosen
    Peter Maas was an American journalist and bestselling author known for his nonfiction crime books and biographies, including the work that inspired the film "King of the Gypsies."
  • B. Peyo
    Peyo was a Belgian cartoonist best known for creating the comic series that introduced the Smurfs.
  • C. Paul Menzel
    Paul Menzel is a relatively obscure individual whose specific public notability is not clearly established from the given information.
  • D. Michael Ernst
    Michael Ernst is a computer scientist known for his work in software engineering and programming languages, including research on type systems and software reliability.
  • E. David Shrigley
    David Shrigley is a British visual artist known for his darkly humorous, cartoon-like drawings, sculptures, and installations that blend absurdity with everyday observations.
  • 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_69d6ab26aae88190b2489efcb2a24234 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a5e760988190b50d13bba5ef5b43 completed April 10, 2026, 7:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69f131cbf9708190ba8394fb3508b975 completed April 28, 2026, 10:16 p.m.
Created at: April 8, 2026, 9:42 p.m.