Triple

T6791863
Position Surface form Disambiguated ID Type / Status
Subject Shanghainese E155949 entity
Predicate mutualIntelligibilityWithMandarin P7448 FINISHED
Object low 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: low | Statement: [Shanghainese, mutualIntelligibilityWithMandarin, low]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mutualIntelligibilityWithMandarin
Context triple: [Shanghainese, mutualIntelligibilityWithMandarin, low]
  • A. areMutuallyIntelligibleToSomeDegree chosen
    Indicates that two or more languages or communication systems can be at least partially understood by each other’s users without prior learning or translation.
  • B. lessMutuallyIntelligibleThan
    Indicates that the level of mutual intelligibility between one pair of languages (or language varieties) is lower than that between another pair.
  • C. hasChineseVersion
    Indicates that an entity has a corresponding version or representation available in Chinese.
  • D. spokenInCanton
    Indicates that something (typically a language, phrase, or communication) is expressed using the Cantonese dialect.
  • E. recognizedAsDistinctLanguageFrom
    Indicates that one language is formally acknowledged or treated as a separate and distinct language from another, rather than as a dialect or variant of it.
  • 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_69c6881770fc8190972b2906390380f5 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d2ae4d1c819089ac6b3abf11a341 completed March 27, 2026, 6:55 p.m.
PD Predicate disambiguation batch_69c6d0979ce0819094678896da4e3169 completed March 27, 2026, 6:46 p.m.
Created at: March 27, 2026, 2:15 p.m.