Triple

T13961341
Position Surface form Disambiguated ID Type / Status
Subject The Herald (Melbourne) E335797 entity
Predicate mediumOfLanguage P28304 FINISHED
Object English-language press in Australia LITERAL 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: English-language press in Australia | Statement: [The Herald (Melbourne), mediumOfLanguage, English-language press in Australia]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mediumOfLanguage
Context triple: [The Herald (Melbourne), mediumOfLanguage, English-language press in Australia]
  • A. typicalLanguages
    Indicates the languages that are commonly or characteristically used, spoken, or associated with a given entity.
  • B. languageUse
    Indicates the language or languages an entity uses for communication, expression, or interaction.
  • C. mediaLanguage chosen
    Indicates the language in which a media item (such as a film, broadcast, or publication) is originally produced or presented.
  • D. languageOfExpression
    Indicates that a particular language is used as the medium or form in which an expression (such as a text, utterance, or work) is realized.
  • E. commonMedium
    Indicates that two or more entities share the same medium or channel through which interaction, communication, or transmission occurs.
  • F. None of above.

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_69d81c61f3508190aaf2ca0dc0002c59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e7c73d48190b8e02971b5a8ed5f completed April 14, 2026, 12:09 p.m.
PD Predicate disambiguation batch_69de05a3ccf88190b45c742db483fa08 completed April 14, 2026, 9:15 a.m.
Created at: April 9, 2026, 10:18 p.m.