Triple

T2356917
Position Surface form Disambiguated ID Type / Status
Subject Tai–Kadai languages E47577 entity
Predicate includesLanguage P2177 FINISHED
Object Hlai language E257936 NE 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: Hlai language | Statement: [Tai–Kadai languages, includesLanguage, Hlai language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hlai language
Context triple: [Tai–Kadai languages, includesLanguage, Hlai language]
  • A. Hlai languages chosen
    Hlai languages are a group of closely related Tai–Kadai languages spoken primarily by the Li (Hlai) people on China’s Hainan Island.
  • B. Lamaholot language
    The Lamaholot language is an Austronesian language spoken primarily in eastern Flores and nearby islands in Indonesia, known for its numerous dialects and complex verbal morphology.
  • C. Hoava language
    The Hoava language is an Oceanic language spoken by communities in the western Solomon Islands, particularly on New Georgia Island.
  • D. Kayeli language
    The Kayeli language is an Austronesian language once spoken on Buru Island in Indonesia, now critically endangered or possibly extinct.
  • E. Saluan language
    The Saluan language is an Austronesian language spoken by the Saluan people of central and eastern Sulawesi, Indonesia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a88a1b678c8190bce986922ba60ce0 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc71e0c68819082eebd80721abcc1 completed March 7, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69aea888b5a881909b1f91562957388d completed March 9, 2026, 11:01 a.m.
Created at: March 4, 2026, 7:54 p.m.