Triple

T18266742
Position Surface form Disambiguated ID Type / Status
Subject Aravind Joshi E437502 entity
Predicate knownFor P22 FINISHED
Object Tree Adjoining Grammar — NE NERFINISHED

How this triple was built (3 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: Tree Adjoining Grammar | Statement: [Aravind Joshi, knownFor, Tree Adjoining Grammar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tree Adjoining Grammar
Context triple: [Aravind Joshi, knownFor, Tree Adjoining Grammar]
  • A. Augmented Transition Network
    Augmented Transition Network is a type of finite-state machine extended with stack-based memory and procedural actions, widely used in natural language processing for parsing complex sentence structures.
  • B. Van Wijngaarden grammars
    Van Wijngaarden grammars are a highly expressive formal grammar formalism, introduced for defining complex programming language syntax and semantics, notably used in the specification of ALGOL 68.
  • C. Aho–Ullman algorithms for parsing
    Aho–Ullman algorithms for parsing are foundational compiler-construction techniques that efficiently analyze and translate the syntactic structure of programming languages based on formal grammar theory.
  • D. Lexical-Functional Grammar
    Lexical-Functional Grammar is a non-transformational theory of syntax that models sentence structure through parallel levels of representation, emphasizing the relationship between grammatical functions and lexical information.
  • E. Augmented Backus–Naur Form
    Augmented Backus–Naur Form (ABNF) is a standardized, extended version of Backus–Naur Form used to formally specify the syntax of languages and protocols, notably in Internet and communication standards.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tree Adjoining Grammar
Target entity description: Tree Adjoining Grammar is a highly structured formal grammar framework in computational linguistics used to model the syntax of natural languages with greater expressive power than context-free grammars.
  • A. Augmented Transition Network
    Augmented Transition Network is a type of finite-state machine extended with stack-based memory and procedural actions, widely used in natural language processing for parsing complex sentence structures.
  • B. Van Wijngaarden grammars
    Van Wijngaarden grammars are a highly expressive formal grammar formalism, introduced for defining complex programming language syntax and semantics, notably used in the specification of ALGOL 68.
  • C. Aho–Ullman algorithms for parsing
    Aho–Ullman algorithms for parsing are foundational compiler-construction techniques that efficiently analyze and translate the syntactic structure of programming languages based on formal grammar theory.
  • D. Lexical-Functional Grammar
    Lexical-Functional Grammar is a non-transformational theory of syntax that models sentence structure through parallel levels of representation, emphasizing the relationship between grammatical functions and lexical information.
  • E. Augmented Backus–Naur Form
    Augmented Backus–Naur Form (ABNF) is a standardized, extended version of Backus–Naur Form used to formally specify the syntax of languages and protocols, notably in Internet and communication standards.
  • F. None of above. chosen

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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ff7af85c81909859e7247738a535 completed April 19, 2026, 4:14 p.m.
Created at: April 10, 2026, 10:34 a.m.