Triple

T12876680
Position Surface form Disambiguated ID Type / Status
Subject Cubeo people E307986 entity
Predicate language P15 FINISHED
Object Cubeo language
Cubeo language is an indigenous Tucanoan language spoken by the Cubeo people of the northwest Amazon region, primarily in Colombia.
E1006431 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: Cubeo language | Statement: [Cubeo people, language, Cubeo language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cubeo language
Context triple: [Cubeo people, language, Cubeo language]
  • A. Keo language
    The Keo language is an Austronesian language spoken by the Keo people on Flores Island in Indonesia.
  • B. Triqui language
    The Triqui language is an Oto-Manguean indigenous language of southern Mexico, spoken primarily by the Triqui people of Oaxaca.
  • C. Argobba language
    The Argobba language is an endangered Ethiosemitic language spoken by the Argobba people of Ethiopia, closely related to Harari and other languages of the Harar region.
  • D. Keka language
    Keka is an Austronesian language spoken on Rote Island in Indonesia, belonging to the Rote subgroup of languages.
  • E. Kuikuro language
    The Kuikuro language is an indigenous Cariban language spoken by the Kuikuro people of Brazil’s Upper Xingu region, known for its rich oral traditions and complex grammatical structure.
  • 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: Cubeo language
Triple: [Cubeo people, language, Cubeo language]
Generated description
Cubeo language is an indigenous Tucanoan language spoken by the Cubeo people of the northwest Amazon region, primarily in Colombia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cubeo language
Target entity description: Cubeo language is an indigenous Tucanoan language spoken by the Cubeo people of the northwest Amazon region, primarily in Colombia.
  • A. Keo language
    The Keo language is an Austronesian language spoken by the Keo people on Flores Island in Indonesia.
  • B. Triqui language
    The Triqui language is an Oto-Manguean indigenous language of southern Mexico, spoken primarily by the Triqui people of Oaxaca.
  • C. Argobba language
    The Argobba language is an endangered Ethiosemitic language spoken by the Argobba people of Ethiopia, closely related to Harari and other languages of the Harar region.
  • D. Keka language
    Keka is an Austronesian language spoken on Rote Island in Indonesia, belonging to the Rote subgroup of languages.
  • E. Kuikuro language
    The Kuikuro language is an indigenous Cariban language spoken by the Kuikuro people of Brazil’s Upper Xingu region, known for its rich oral traditions and complex grammatical structure.
  • 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_69d7bdf69bc48190af6c2621f28ca351 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d970f97f9c81908c75259a4cab1d3c completed April 10, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69bb83bac8190838f7537b806317c completed May 3, 2026, 12:50 a.m.
NEDg Description generation batch_69f69cc60c488190a5a71e25c075e9ff completed May 3, 2026, 12:54 a.m.
NED2 Entity disambiguation (via description) batch_69f69d845a9081909b40562825c1c500 completed May 3, 2026, 12:57 a.m.
Created at: April 9, 2026, 5:38 p.m.