Triple

T1835196
Position Surface form Disambiguated ID Type / Status
Subject z/OS E41049 entity
Predicate supports P516 FINISHED
Object COBOL E204900 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: COBOL | Statement: [z/OS, supports, COBOL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: COBOL
Context triple: [z/OS, supports, COBOL]
  • A. COBOL chosen
    COBOL is a long-established, English-like programming language primarily used for business, finance, and administrative systems on mainframes and enterprise platforms.
  • B. PL/I
    PL/I is a high-level programming language developed by IBM in the 1960s that combines features from scientific, business, and systems programming languages into a single, general-purpose language.
  • C. BCPL
    BCPL (Basic Combined Programming Language) is an early, typeless systems programming language developed in the 1960s that significantly influenced the design of the C programming language.
  • D. Fortran
    Fortran is a high-level programming language, particularly strong in numerical and scientific computing, widely used for engineering, physics, and high-performance applications.
  • 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 (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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb026aa7c8190bc988d3ee0fd9f41 completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9b4b4f08190a0e5ad50de5c0ba8 completed March 8, 2026, 7:10 p.m.
Created at: March 4, 2026, 7:33 p.m.