Triple

T20565028
Position Surface form Disambiguated ID Type / Status
Subject Cham Malay E504944 entity
Predicate languageBranch P1967 FINISHED
Object Malayic 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: Malayic | Statement: [Cham Malay, languageBranch, Malayic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malayic
Context triple: [Cham Malay, languageBranch, Malayic]
  • A. Malayic languages chosen
    Malayic languages are a subgroup of the Austronesian language family that includes Malay, Indonesian, and closely related languages spoken primarily in Maritime Southeast Asia.
  • B. Bawean Malay
    Bawean Malay is an Austronesian language variety closely related to Malay and spoken primarily by the Baweanese community on Bawean Island in Indonesia.
  • C. Bacan Malay
    Bacan Malay is an Austronesian language spoken on Bacan Island in North Maluku, Indonesia, notable for its unique development as a Malay variety isolated from other Malay-speaking regions.
  • D. Badimaya language
    Badimaya language is an Australian Aboriginal language traditionally spoken by the Yamatji people of Western Australia.
  • E. Cham Malay
    Cham Malay is a historical Austronesian language variety associated with the Cham people, written in the Arabic-derived Jawi script and influenced by Malay and regional Islamic culture.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a15c988190ba93823df119ca4d completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.