Triple

T10072023
Position Surface form Disambiguated ID Type / Status
Subject Eastern Malayo-Polynesian languages E213651 entity
Predicate includesLanguage P2177 FINISHED
Object Buli
Buli is an Austronesian language spoken primarily on Halmahera Island in eastern Indonesia.
 E839377 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: Buli | Statement: [Eastern Malayo-Polynesian languages, includesLanguage, Buli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Buli
Context triple: [Eastern Malayo-Polynesian languages, includesLanguage, Buli]
  • A. Buli
    Buli is a barangay (village-level administrative division) within the city of Muntinlupa in Metro Manila, Philippines.
  • B. Barkly
    Barkly is a vast electoral division in Australia's Northern Territory, encompassing remote outback communities and pastoral regions including the Tennant Creek area.
  • C. Puli
    Puli is a township in central Taiwan known for its indigenous communities, including Kaxabu speakers, and its role as a cultural and geographic hub in Nantou County.
  • D. Shepshed
    Shepshed is a town in the English East Midlands known historically for its textile industry and now as a residential community near Loughborough in Leicestershire.
  • E. Merle
    Merle is a given name most famously associated with American country music legend Merle Haggard.
  • 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: Buli
Triple: [Eastern Malayo-Polynesian languages, includesLanguage, Buli]
Generated description
Buli is an Austronesian language spoken primarily on Halmahera Island in eastern Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Buli
Target entity description: Buli is an Austronesian language spoken primarily on Halmahera Island in eastern Indonesia.
  • A. Buli
    Buli is a barangay (village-level administrative division) within the city of Muntinlupa in Metro Manila, Philippines.
  • B. Barkly
    Barkly is a vast electoral division in Australia's Northern Territory, encompassing remote outback communities and pastoral regions including the Tennant Creek area.
  • C. Puli
    Puli is a township in central Taiwan known for its indigenous communities, including Kaxabu speakers, and its role as a cultural and geographic hub in Nantou County.
  • D. Shepshed
    Shepshed is a town in the English East Midlands known historically for its textile industry and now as a residential community near Loughborough in Leicestershire.
  • E. Merle
    Merle is a given name most famously associated with American country music legend Merle Haggard.
  • 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_69ca839add308190b57d53b4ec21f2d0 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd013c9d0819091ebe6fc399832de completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29aaa61308190b134b49a6c1c1131 completed April 5, 2026, 5:23 p.m.
NEDg Description generation batch_69d29e8617c08190bf4fb02ac40caba3 completed April 5, 2026, 5:40 p.m.
NED2 Entity disambiguation (via description) batch_69d29f20b2f48190906d7e53fb1e5544 completed April 5, 2026, 5:42 p.m.
Created at: March 30, 2026, 8:59 p.m.