Triple

T22031592
Position Surface form Disambiguated ID Type / Status
Subject Toishan dialect E544099 entity
Predicate alternativeName P39 FINISHED
Object Hoisanese 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: Hoisanese | Statement: [Toishan dialect, alternativeName, Hoisanese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hoisanese
Context triple: [Toishan dialect, alternativeName, Hoisanese]
  • A. Hoisanese chosen
    Hoisanese is a Yue Chinese dialect spoken primarily by people from Taishan in Guangdong, China, and their overseas communities.
  • B. Hoisan
    Hoisan is an older romanization of Taishan, a county-level city in Guangdong, China, historically known for its large overseas Chinese diaspora.
  • C. Nagamese
    Nagamese is a widely used Assamese-based creole lingua franca in Nagaland, India, facilitating communication among diverse Naga ethnic groups.
  • D. Bugis
    The Bugis are a seafaring Austronesian ethnic group from South Sulawesi, Indonesia, known historically as skilled sailors, traders, and navigators.
  • E. Bugis
    Bugis is a vibrant commercial and cultural district in Singapore known for its shopping streets, markets, and nightlife.
  • 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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127edd5b48190a9aeb2840105c181 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:24 p.m.