Triple

T1565877
Position Surface form Disambiguated ID Type / Status
Subject Ha people E33431 entity
Predicate language P15 FINISHED
Object Ha language
Ha language is a Bantu language spoken primarily by the Ha people in western Tanzania, particularly around the shores of Lake Tanganyika.
E177051 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: Ha language | Statement: [Ha people, language, Ha language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ha language
Context triple: [Ha people, language, Ha language]
  • A. Hoava language
    The Hoava language is an Oceanic language spoken by communities in the western Solomon Islands, particularly on New Georgia Island.
  • B. Hadza language
    The Hadza language is an isolate spoken by the Hadza people of northern Tanzania, notable for its extensive use of click consonants and lack of clear genetic affiliation to other language families.
  • C. Hoanya language
    The Hoanya language is an extinct Austronesian language once spoken by the Hoanya people of western Taiwan and classified among the indigenous Formosan languages.
  • D. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • E. Busoa language
    The Busoa language is an Austronesian language spoken by a small community in Southeast Sulawesi, 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: Ha language
Triple: [Ha people, language, Ha language]
Generated description
Ha language is a Bantu language spoken primarily by the Ha people in western Tanzania, particularly around the shores of Lake Tanganyika.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ha language
Target entity description: Ha language is a Bantu language spoken primarily by the Ha people in western Tanzania, particularly around the shores of Lake Tanganyika.
  • A. Hoava language
    The Hoava language is an Oceanic language spoken by communities in the western Solomon Islands, particularly on New Georgia Island.
  • B. Hadza language
    The Hadza language is an isolate spoken by the Hadza people of northern Tanzania, notable for its extensive use of click consonants and lack of clear genetic affiliation to other language families.
  • C. Hoanya language
    The Hoanya language is an extinct Austronesian language once spoken by the Hoanya people of western Taiwan and classified among the indigenous Formosan languages.
  • D. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • E. Busoa language
    The Busoa language is an Austronesian language spoken by a small community in Southeast Sulawesi, 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_69a885f11b048190935025a035302715 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb2308bec81909d1660934eff171b completed March 7, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad3719dfdc819085511f96f9f92dba completed March 8, 2026, 8:45 a.m.
NEDg Description generation batch_69ad37d59e94819085504ea25dfa8311 completed March 8, 2026, 8:48 a.m.
NED2 Entity disambiguation (via description) batch_69ad382b126c8190a308415bd6c4264b completed March 8, 2026, 8:49 a.m.
Created at: March 4, 2026, 7:27 p.m.