Triple

T1945902
Position Surface form Disambiguated ID Type / Status
Subject Austroasiatic E42054 entity
Predicate hasLanguage P15 FINISHED
Object Wa language
The Wa language is a Mon–Khmer language spoken primarily by the Wa people in parts of Myanmar and China.
 E220623 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: Wa language | Statement: [Austroasiatic, hasLanguage, Wa language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wa language
Context triple: [Austroasiatic, hasLanguage, Wa language]
  • A. Kwaio language
    The Kwaio language is an Austronesian language spoken by the Kwaio people on Malaita in the Solomon Islands.
  • B. Wapishana language
    The Wapishana language is an indigenous Arawakan language spoken primarily by the Wapishana people in parts of Brazil and Guyana.
  • C. Ha language
    Ha language is a Bantu language spoken primarily by the Ha people in western Tanzania, particularly around the shores of Lake Tanganyika.
  • D. Kwa languages
    Kwa languages are a major branch of the Niger-Congo language family spoken primarily in southern West Africa, including parts of Ghana, Côte d’Ivoire, Togo, and Benin.
  • E. Wewewa language
    The Wewewa language is an Austronesian language spoken by the Wewewa people on the western part of Sumba Island in eastern Indonesia.
  • 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: Wa language
Triple: [Austroasiatic, hasLanguage, Wa language]
Generated description
The Wa language is a Mon–Khmer language spoken primarily by the Wa people in parts of Myanmar and China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wa language
Target entity description: The Wa language is a Mon–Khmer language spoken primarily by the Wa people in parts of Myanmar and China.
  • A. Kwaio language
    The Kwaio language is an Austronesian language spoken by the Kwaio people on Malaita in the Solomon Islands.
  • B. Wapishana language
    The Wapishana language is an indigenous Arawakan language spoken primarily by the Wapishana people in parts of Brazil and Guyana.
  • C. Ha language
    Ha language is a Bantu language spoken primarily by the Ha people in western Tanzania, particularly around the shores of Lake Tanganyika.
  • D. Kwa languages
    Kwa languages are a major branch of the Niger-Congo language family spoken primarily in southern West Africa, including parts of Ghana, Côte d’Ivoire, Togo, and Benin.
  • E. Wewewa language
    The Wewewa language is an Austronesian language spoken by the Wewewa people on the western part of Sumba Island in eastern Indonesia.
  • 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_69a8870e08fc8190a319cbf2600db15f completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb300af2481908ae359972843c1ef completed March 7, 2026, 5:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfbbcc5688190aad081dc8d119e7f completed March 8, 2026, 10:44 p.m.
NEDg Description generation batch_69adfc50a3488190afe44ee5125d9ebd completed March 8, 2026, 10:46 p.m.
NED2 Entity disambiguation (via description) batch_69adfcdccce48190a2591b90c81ad084 completed March 8, 2026, 10:49 p.m.
Created at: March 4, 2026, 7:36 p.m.