Triple

T18292984
Position Surface form Disambiguated ID Type / Status
Subject Focus Groups of ITU-T E438161 entity
Predicate usesLanguage P238 FINISHED
Object English 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: English | Statement: [Focus Groups of ITU-T, usesLanguage, English]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: English
Context triple: [Focus Groups of ITU-T, usesLanguage, English]
  • A. English chosen
    English is a widely spoken West Germanic language that serves as a global lingua franca in education, business, science, and international communication.
  • B. Inglis
    Inglis is a surname most prominently associated with Australian rugby league star Greg Inglis.
  • C. ENG
    ENG is the three-letter FIFA country code used to represent the England national football team in international competitions and official records.
  • D. EN
    EN is the standard abbreviation used in Portugal for "Estrada Nacional," the national road network.
  • E. Angolalla
    Angolalla is a historic town in central Ethiopia known as the birthplace of Emperor Menelik II.
  • 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_69d8b915e3e881909125d760c15d0c29 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50100d6488190bbe73668df9c4046 completed April 19, 2026, 4:21 p.m.
Created at: April 10, 2026, 10:35 a.m.