Triple

T16430510
Position Surface form Disambiguated ID Type / Status
Subject GEOS-IT E399059 entity
Predicate language P15 FINISHED
Object Fortran (core model implementation) E59594 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: Fortran (core model implementation) | Statement: [GEOS-IT, language, Fortran (core model implementation)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fortran (core model implementation)
Context triple: [GEOS-IT, language, Fortran (core model implementation)]
  • 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. IBM 7090 FORTRAN compiler
    The IBM 7090 FORTRAN compiler was an early high-level language compiler developed by IBM for its 7090 mainframe, widely used in the 1960s for scientific and engineering computing.
  • D. Fortress programming language
    Fortress is a high-performance, mathematically oriented experimental programming language designed to explore parallelism and productivity in scientific and technical computing.
  • E. Algol 68R
    Algol 68R is a revised, more practical and implementable version of the Algol 68 programming language, created to simplify and clarify the original language’s complex design.
  • 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_69d87f2b9024819085c20e52de95d583 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e328fe0f488190ac34aa677c980a20 completed April 18, 2026, 6:47 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004584fa508190a85b1f79ecf9c258 completed May 10, 2026, 8:44 a.m.
Created at: April 10, 2026, 5:10 a.m.