Triple

T1054904
Position Surface form Disambiguated ID Type / Status
Subject Xinjiang E22779 entity
Predicate ethnicGroup P194 FINISHED
Object Xibe
The Xibe are a Tungusic-speaking ethnic minority in China, culturally related to the Manchu and known for their historical role as frontier garrisons in regions such as Xinjiang.
 E124647 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: Xibe | Statement: [Xinjiang, ethnicGroup, Xibe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Xibe
Context triple: [Xinjiang, ethnicGroup, Xibe]
  • A. Ngobe
    Ngobe is an alternative transliteration of Ngäbere, the language of the Ngäbe (Guaymí) Indigenous people of Panama and Costa Rica.
  • B. Lozi
    Lozi is a Bantu language spoken primarily by the Lozi people in western Zambia and surrounding regions of southern Africa.
  • C. Toubou
    Toubou are a traditionally nomadic Saharan ethnic group primarily inhabiting northern Chad, southern Libya, and surrounding regions.
  • D. Beni
    Beni is a sparsely populated, largely Amazonian department in northeastern Bolivia known for its tropical lowlands, cattle ranching, and rich indigenous cultures.
  • E. Ngäbe
    Ngäbe are an Indigenous people of Central America, primarily living in Panama and Costa Rica, known for their distinct Ngäbere language and rich cultural traditions.
  • 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: Xibe
Triple: [Xinjiang, ethnicGroup, Xibe]
Generated description
The Xibe are a Tungusic-speaking ethnic minority in China, culturally related to the Manchu and known for their historical role as frontier garrisons in regions such as Xinjiang.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Xibe
Target entity description: The Xibe are a Tungusic-speaking ethnic minority in China, culturally related to the Manchu and known for their historical role as frontier garrisons in regions such as Xinjiang.
  • A. Ngobe
    Ngobe is an alternative transliteration of Ngäbere, the language of the Ngäbe (Guaymí) Indigenous people of Panama and Costa Rica.
  • B. Lozi
    Lozi is a Bantu language spoken primarily by the Lozi people in western Zambia and surrounding regions of southern Africa.
  • C. Toubou
    Toubou are a traditionally nomadic Saharan ethnic group primarily inhabiting northern Chad, southern Libya, and surrounding regions.
  • D. Beni
    Beni is a sparsely populated, largely Amazonian department in northeastern Bolivia known for its tropical lowlands, cattle ranching, and rich indigenous cultures.
  • E. Ngäbe
    Ngäbe are an Indigenous people of Central America, primarily living in Panama and Costa Rica, known for their distinct Ngäbere language and rich cultural traditions.
  • 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_69a493da02e081908c13ff5e02a0fe7a completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b8d79268819080f3f3f497e91c58 completed March 1, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac429f0580819082d5a2cc6129cb1e completed March 7, 2026, 3:22 p.m.
NEDg Description generation batch_69ac4356f8f88190ab5d3f76000d5352 completed March 7, 2026, 3:25 p.m.
NED2 Entity disambiguation (via description) batch_69ac43ded4308190bbedda3e2c6255a4 completed March 7, 2026, 3:27 p.m.
Created at: March 1, 2026, 7:42 p.m.