Triple

T38670847
Position Surface form Disambiguated ID Type / Status
Subject Sarah Norman E940580 entity
Predicate communicatesPrimarilyThrough P59911 FINISHED
Object sign language 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: sign language | Statement: [Sarah Norman, communicatesPrimarilyThrough, sign language]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: communicatesPrimarilyThrough
Context triple: [Sarah Norman, communicatesPrimarilyThrough, sign language]
  • A. spokenPrimarilyOn
    Indicates that something (typically a language or dialect) is used mainly for spoken communication in a particular context, region, or group.
  • B. primaryLanguageContact
    Indicates that one language serves as the main or dominant medium of communication in a particular contact situation between language communities.
  • C. languageOfCommunications
    Indicates that a specified language is used as the medium for communications associated with an entity or interaction.
  • 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. usedToCommunicate chosen
    Indicates that one entity serves as a medium or tool through which another entity conveys information, messages, or signals.
  • 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_69f76edfde348190bf6529d9f49ecd62 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fcdfbc71c481908ba7f87907b17782 completed May 7, 2026, 6:53 p.m.
PD Predicate disambiguation batch_69fcdbe580b8819087f143596b2c79c0 completed May 7, 2026, 6:37 p.m.
Created at: May 3, 2026, 4:33 p.m.