Triple

T9694409
Position Surface form Disambiguated ID Type / Status
Subject Mapudungun E234610 entity
Predicate hasDialects P4251 FINISHED
Object Nguluche
Nguluche is a regional dialect variety of the Mapudungun language spoken by the Mapuche people of southern South America.
 E815788 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: Nguluche | Statement: [Mapudungun, hasDialects, Nguluche]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nguluche
Context triple: [Mapudungun, hasDialects, Nguluche]
  • A. Oshindali
    Oshindali is a regional dialect of the Oshiwambo language spoken primarily by communities in northern Namibia and southern Angola.
  • B. Makonde
    Makonde is a Bantu language spoken primarily by the Makonde people of northern Mozambique and southern Tanzania.
  • C. Njideka
    Njideka is a feminine given name of Igbo origin, commonly used in Nigeria.
  • D. Raila
    Raila is a prominent Kenyan politician and longtime opposition leader who has played a major role in the country’s democratic reforms.
  • E. Uma Mbatangu
    Uma Mbatangu is a traditional Sumbanese house type characterized by its tall peaked thatched roof and elevated wooden structure, commonly found in the Waikabubak area of 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: Nguluche
Triple: [Mapudungun, hasDialects, Nguluche]
Generated description
Nguluche is a regional dialect variety of the Mapudungun language spoken by the Mapuche people of southern South America.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nguluche
Target entity description: Nguluche is a regional dialect variety of the Mapudungun language spoken by the Mapuche people of southern South America.
  • A. Oshindali
    Oshindali is a regional dialect of the Oshiwambo language spoken primarily by communities in northern Namibia and southern Angola.
  • B. Makonde
    Makonde is a Bantu language spoken primarily by the Makonde people of northern Mozambique and southern Tanzania.
  • C. Njideka
    Njideka is a feminine given name of Igbo origin, commonly used in Nigeria.
  • D. Raila
    Raila is a prominent Kenyan politician and longtime opposition leader who has played a major role in the country’s democratic reforms.
  • E. Uma Mbatangu
    Uma Mbatangu is a traditional Sumbanese house type characterized by its tall peaked thatched roof and elevated wooden structure, commonly found in the Waikabubak area of 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_69ca84cb580c8190a7e5f4b3bcdaf2a4 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9d348868819083aec7a5da8c455b completed April 1, 2026, 10:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1911d33f081908637cbf4c1949bcd completed April 4, 2026, 10:30 p.m.
NEDg Description generation batch_69d19533ef1c8190926ffb4eb92b8ef4 completed April 4, 2026, 10:48 p.m.
NED2 Entity disambiguation (via description) batch_69d195b69a4c8190941b92cc36bdc416 completed April 4, 2026, 10:50 p.m.
Created at: March 30, 2026, 8:17 p.m.