Triple

T2356921
Position Surface form Disambiguated ID Type / Status
Subject Tai–Kadai languages E47577 entity
Predicate includesLanguage P2177 FINISHED
Object Lakkia language
The Lakkia language is a lesser-known Tai–Kadai language spoken by the Lakkia ethnic group in parts of southern China, notable for its unique blend of Tai–Kadai and Hmong–Mien linguistic features.
 E257939 NE FINISHED

How this triple was built (4 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: Lakkia language | Statement: [Tai–Kadai languages, includesLanguage, Lakkia language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lakkia language
Context triple: [Tai–Kadai languages, includesLanguage, Lakkia language]
  • A. Lakalai language
    The Lakalai language is an Austronesian language spoken by the Lakalai people of New Britain in Papua New Guinea.
  • B. Nalik language
    The Nalik language is an Austronesian language spoken primarily on New Ireland in Papua New Guinea by the Nalik people.
  • C. Sakizaya language
    The Sakizaya language is an indigenous Austronesian language spoken by the Sakizaya people of eastern Taiwan.
  • D. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • E. Kharia language
    Kharia language is a Munda language spoken primarily by the Kharia people in eastern India, especially in the states of Jharkhand, Odisha, and Chhattisgarh.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lakkia language
Triple: [Tai–Kadai languages, includesLanguage, Lakkia language]
Generated description
The Lakkia language is a lesser-known Tai–Kadai language spoken by the Lakkia ethnic group in parts of southern China, notable for its unique blend of Tai–Kadai and Hmong–Mien linguistic features.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lakkia language
Target entity description: The Lakkia language is a lesser-known Tai–Kadai language spoken by the Lakkia ethnic group in parts of southern China, notable for its unique blend of Tai–Kadai and Hmong–Mien linguistic features.
  • A. Lakalai language
    The Lakalai language is an Austronesian language spoken by the Lakalai people of New Britain in Papua New Guinea.
  • B. Nalik language
    The Nalik language is an Austronesian language spoken primarily on New Ireland in Papua New Guinea by the Nalik people.
  • C. Sakizaya language
    The Sakizaya language is an indigenous Austronesian language spoken by the Sakizaya people of eastern Taiwan.
  • D. Logba language
    The Logba language is a Niger-Congo language spoken by the Logba people of southeastern Ghana.
  • E. Kharia language
    Kharia language is a Munda language spoken primarily by the Kharia people in eastern India, especially in the states of Jharkhand, Odisha, and Chhattisgarh.
  • F. None of above. chosen

Provenance (5 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_69ae9638ef948190adf945aba42fac76 completed March 9, 2026, 9:43 a.m.
NEDg Description generation batch_69ae96fc0b508190b1da6aa41cddc488 completed March 9, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_69ae977e539c81909cef638cc61e5ec1 completed March 9, 2026, 9:48 a.m.
Created at: March 4, 2026, 7:54 p.m.