Triple

T15277972
Position Surface form Disambiguated ID Type / Status
Subject Tucanoan languages E365192 entity
Predicate hasMemberLanguage P7390 FINISHED
Object Desano
Desano is an indigenous Tucanoan language spoken primarily by the Desano people in the northwestern Amazon region of Colombia and Brazil.
E1148025 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: Desano | Statement: [Tucanoan languages, hasMemberLanguage, Desano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Desano
Context triple: [Tucanoan languages, hasMemberLanguage, Desano]
  • A. Deshnoke
    Deshnoke is a small town in Rajasthan, India, best known for the Karni Mata Temple, where thousands of rats are revered and protected.
  • B. Desulo
    Desulo is a mountain village in central Sardinia, Italy, known as a traditional gateway to the island’s highest peak and for its well-preserved pastoral culture and customs.
  • C. Dosso
    Dosso is a key town in southwestern Niger that serves as an important regional and transportation hub.
  • D. Deshay
    Deshay is a variant transliteration of the Indian surname "Desai," commonly associated with communities in western India.
  • E. Desaix
    Desaix is a French surname most notably associated with General Louis Desaix, a prominent military leader during the French Revolutionary Wars.
  • 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: Desano
Triple: [Tucanoan languages, hasMemberLanguage, Desano]
Generated description
Desano is an indigenous Tucanoan language spoken primarily by the Desano people in the northwestern Amazon region of Colombia and Brazil.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Desano
Target entity description: Desano is an indigenous Tucanoan language spoken primarily by the Desano people in the northwestern Amazon region of Colombia and Brazil.
  • A. Deshnoke
    Deshnoke is a small town in Rajasthan, India, best known for the Karni Mata Temple, where thousands of rats are revered and protected.
  • B. Desulo
    Desulo is a mountain village in central Sardinia, Italy, known as a traditional gateway to the island’s highest peak and for its well-preserved pastoral culture and customs.
  • C. Dosso
    Dosso is a key town in southwestern Niger that serves as an important regional and transportation hub.
  • D. Deshay
    Deshay is a variant transliteration of the Indian surname "Desai," commonly associated with communities in western India.
  • E. Desaix
    Desaix is a French surname most notably associated with General Louis Desaix, a prominent military leader during the French Revolutionary Wars.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00953bc848190b83919f39d5ee37b completed April 15, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef734f488190951d029183d456f5 completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef154c11c8190b07efafe1252d8eb completed May 9, 2026, 8:33 a.m.
NED2 Entity disambiguation (via description) batch_69fef1b895f08190bedf6274b70f6d90 completed May 9, 2026, 8:35 a.m.
Created at: April 10, 2026, 3:14 a.m.