Triple

T2169671
Position Surface form Disambiguated ID Type / Status
Subject Nikolaj Bjørner E46992 entity
Predicate programmingLanguage P1592 FINISHED
Object OCaml E131758 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: OCaml | Statement: [Nikolaj Bjørner, programmingLanguage, OCaml]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OCaml
Context triple: [Nikolaj Bjørner, programmingLanguage, OCaml]
  • A. OCaml chosen
    OCaml is a statically typed functional programming language from the ML family, known for its powerful type system, pattern matching, and efficient native code compilation.
  • B. ReasonML
    ReasonML is a syntax and toolchain for the OCaml language that offers a JavaScript-friendly, type-safe alternative for building web and native applications.
  • C. Standard ML
    Standard ML is a statically typed functional programming language with type inference and a formal semantics, widely used in programming language research and teaching.
  • D. F#
    F# is a functional-first, multi-paradigm programming language for the .NET platform, known for its strong type system and concise, expressive syntax.
  • E. coq gaulois
    Coq gaulois is the French term for the Gallic rooster, a national emblem of France symbolizing courage, pride, and the French nation.
  • 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_69a88a184cbc8190877791f6552c2484 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbeaeb58881908ad34f7b253bac2a completed March 7, 2026, 5:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae58f511a08190880fbde8900d59df completed March 9, 2026, 5:21 a.m.
Created at: March 4, 2026, 7:45 p.m.