Triple

T6469591
Position Surface form Disambiguated ID Type / Status
Subject Tupian E142313 entity
Predicate wellKnownLanguage P42338 FINISHED
Object Cinta Larga language
The Cinta Larga language is an indigenous Tupian language spoken by the Cinta Larga people of the Brazilian Amazon.
E596817 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: Cinta Larga language | Statement: [Tupian, wellKnownLanguage, Cinta Larga language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cinta Larga language
Context triple: [Tupian, wellKnownLanguage, Cinta Larga language]
  • A. Arte de la lengua yunga
    Arte de la lengua yunga is a colonial-era grammatical and lexical description of the Mochica (Yunga) language, created by missionaries to document and facilitate its study and use.
  • B. Lange
    Lange is a German surname borne by numerous notable individuals across fields such as science, politics, arts, and sports.
  • C. Limba
    The Limba are one of the largest and oldest indigenous ethnic groups in Sierra Leone, known for their distinct language, cultural traditions, and historical role in the country’s northern regions.
  • D. Longo
    Longo is an Italian surname borne by various notable figures in politics, arts, and sports.
  • E. Langer
    Langer is a surname most notably associated with Robert Langer, a pioneering American chemical engineer and prolific inventor in biotechnology and drug delivery.
  • 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: Cinta Larga language
Triple: [Tupian, wellKnownLanguage, Cinta Larga language]
Generated description
The Cinta Larga language is an indigenous Tupian language spoken by the Cinta Larga people of the Brazilian Amazon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cinta Larga language
Target entity description: The Cinta Larga language is an indigenous Tupian language spoken by the Cinta Larga people of the Brazilian Amazon.
  • A. Arte de la lengua yunga
    Arte de la lengua yunga is a colonial-era grammatical and lexical description of the Mochica (Yunga) language, created by missionaries to document and facilitate its study and use.
  • B. Lange
    Lange is a German surname borne by numerous notable individuals across fields such as science, politics, arts, and sports.
  • C. Limba
    The Limba are one of the largest and oldest indigenous ethnic groups in Sierra Leone, known for their distinct language, cultural traditions, and historical role in the country’s northern regions.
  • D. Longo
    Longo is an Italian surname borne by various notable figures in politics, arts, and sports.
  • E. Langer
    Langer is a surname most notably associated with Robert Langer, a pioneering American chemical engineer and prolific inventor in biotechnology and drug delivery.
  • 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.