Triple

T10268215
Position Surface form Disambiguated ID Type / Status
Subject Kadazan-Dusun E240765 entity
Predicate traditionalDance P1114 FINISHED
Object Sumazau
Sumazau is a traditional Kadazan-Dusun dance from Sabah, Malaysia, characterized by graceful, bird-like arm movements performed to gong music during cultural and ceremonial occasions.
 E853072 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: Sumazau | Statement: [Kadazan-Dusun, traditionalDance, Sumazau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sumazau
Context triple: [Kadazan-Dusun, traditionalDance, Sumazau]
  • A. Zezuru
    Zezuru is a major dialect of the Shona language spoken primarily in central and northern Zimbabwe.
  • B. Zakumi
    Zakumi is the leopard-themed mascot character created to represent South Africa and embody the spirit of the 2010 FIFA World Cup.
  • C. Nakoruru
    Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
  • D. Amuesha
    Amuesha is another name for the Yaneshaʼ language, an Arawakan language spoken by the Yaneshaʼ (Amuesha) people of central Peru.
  • E. Munefusa
    Munefusa is the birth name of Matsuo Bashō, the renowned 17th-century Japanese haiku poet and travel writer.
  • 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: Sumazau
Triple: [Kadazan-Dusun, traditionalDance, Sumazau]
Generated description
Sumazau is a traditional Kadazan-Dusun dance from Sabah, Malaysia, characterized by graceful, bird-like arm movements performed to gong music during cultural and ceremonial occasions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sumazau
Target entity description: Sumazau is a traditional Kadazan-Dusun dance from Sabah, Malaysia, characterized by graceful, bird-like arm movements performed to gong music during cultural and ceremonial occasions.
  • A. Zezuru
    Zezuru is a major dialect of the Shona language spoken primarily in central and northern Zimbabwe.
  • B. Zakumi
    Zakumi is the leopard-themed mascot character created to represent South Africa and embody the spirit of the 2010 FIFA World Cup.
  • C. Nakoruru
    Nakoruru is a popular Samurai Shodown character known as a nature-loving Ainu shrine maiden who fights alongside her hawk and wolf companions.
  • D. Amuesha
    Amuesha is another name for the Yaneshaʼ language, an Arawakan language spoken by the Yaneshaʼ (Amuesha) people of central Peru.
  • E. Munefusa
    Munefusa is the birth name of Matsuo Bashō, the renowned 17th-century Japanese haiku poet and travel writer.
  • 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_69d381a94c1881908fc38fc263d9b9c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d26df80081908514fd5c9392e2b7 completed April 7, 2026, 9:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f805d49c8190becddbbf17ac65fd completed April 9, 2026, 12:51 a.m.
NEDg Description generation batch_69d6fcaca55c81908a48ac2a0ce24b85 completed April 9, 2026, 1:11 a.m.
NED2 Entity disambiguation (via description) batch_69d6fd772bc08190bf270f5fc767fb29 completed April 9, 2026, 1:14 a.m.
Created at: April 6, 2026, 11:34 a.m.