Triple

T6469524
Position Surface form Disambiguated ID Type / Status
Subject Tupi–Guaraní E142312 entity
Predicate hasLanguage P15 FINISHED
Object Kayabí
Kayabí is an indigenous Tupi–Guaraní language spoken by the Kayabí people of Brazil.
 E596792 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: Kayabí | Statement: [Tupi–Guaraní, hasLanguage, Kayabí]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kayabí
Context triple: [Tupi–Guaraní, hasLanguage, Kayabí]
  • A. Keiyo
    Keiyo is a Southern Nilotic language spoken primarily by the Keiyo people of Kenya’s Rift Valley region.
  • B. Haruna
    Haruna was a Japanese Kongō-class fast battleship that served in the Imperial Japanese Navy during both World Wars and saw extensive action in the Pacific Theater.
  • C. Katayun
    Katayun is a figure in Persian mythology known primarily as the mother of the legendary hero Esfandiyar in the Shahnameh.
  • D. Machimura
    Machimura is a Japanese surname most notably associated with Nobutaka Machimura, a prominent Liberal Democratic Party politician and former foreign minister of Japan.
  • E. Kampaku
    Kampaku was a powerful regent position in Japan’s imperial court, typically held by senior aristocrats who governed on behalf of an adult emperor.
  • 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: Kayabí
Triple: [Tupi–Guaraní, hasLanguage, Kayabí]
Generated description
Kayabí is an indigenous Tupi–Guaraní language spoken by the Kayabí people of Brazil.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kayabí
Target entity description: Kayabí is an indigenous Tupi–Guaraní language spoken by the Kayabí people of Brazil.
  • A. Keiyo
    Keiyo is a Southern Nilotic language spoken primarily by the Keiyo people of Kenya’s Rift Valley region.
  • B. Haruna
    Haruna was a Japanese Kongō-class fast battleship that served in the Imperial Japanese Navy during both World Wars and saw extensive action in the Pacific Theater.
  • C. Katayun
    Katayun is a figure in Persian mythology known primarily as the mother of the legendary hero Esfandiyar in the Shahnameh.
  • D. Machimura
    Machimura is a Japanese surname most notably associated with Nobutaka Machimura, a prominent Liberal Democratic Party politician and former foreign minister of Japan.
  • E. Kampaku
    Kampaku was a powerful regent position in Japan’s imperial court, typically held by senior aristocrats who governed on behalf of an adult emperor.
  • 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_69c008d3bf4c8190bcf798c5ba9d6fb3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06a16272c81909313455002cd884d completed March 22, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6539a16648190ba5146a292d61ce7 completed March 27, 2026, 9:53 a.m.
NEDg Description generation batch_69c6578825d88190a7f9da7a4f3cdfc9 completed March 27, 2026, 10:10 a.m.
NED2 Entity disambiguation (via description) batch_69c657e45ff88190a169e159bba142f5 completed March 27, 2026, 10:11 a.m.
Created at: March 22, 2026, 4:50 p.m.