Triple

T17919330
Position Surface form Disambiguated ID Type / Status
Subject Don Woods E448023 entity
Predicate programmedIn P27366 FINISHED
Object Fortran 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: Fortran | Statement: [Don Woods, programmedIn, Fortran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fortran
Context triple: [Don Woods, programmedIn, Fortran]
  • A. Fortran chosen
    Fortran is a high-level programming language, particularly strong in numerical and scientific computing, widely used for engineering, physics, and high-performance applications.
  • B. NAG Fortran Compiler
    NAG Fortran Compiler is a commercial, standards-focused Fortran compiler from the Numerical Algorithms Group, widely used for its rigorous support of modern Fortran features and robust error checking.
  • C. Algol 68C
    Algol 68C is a compiler implementation of the Algol 68 programming language, designed to translate its advanced structured constructs into executable machine code.
  • D. Algol 68S
    Algol 68S is a simplified subset of the Algol 68 programming language designed to make the language easier to implement and use.
  • E. Algol 68
    Algol 68 is a high-level, structured programming language from the ALGOL family, notable for its orthogonal design and influence on many later languages.
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4a30844548190b7a43c2f093f35d7 completed April 19, 2026, 9:40 a.m.
Created at: April 10, 2026, 10:20 a.m.