Triple

T1223930
Position Surface form Disambiguated ID Type / Status
Subject Malayo-Polynesian languages E26283 entity
Predicate historicalOrigin P1823 FINISHED
Object Taiwan (Austronesian homeland hypothesis)
Taiwan (Austronesian homeland hypothesis) is a linguistic and archaeological theory proposing that the Austronesian language family originated in Taiwan before spreading across Island Southeast Asia and the Pacific.
E25857 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: Taiwan (Austronesian homeland hypothesis) | Statement: [Malayo-Polynesian languages, historicalOrigin, Taiwan (Austronesian homeland hypothesis)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taiwan (Austronesian homeland hypothesis)
Context triple: [Malayo-Polynesian languages, historicalOrigin, Taiwan (Austronesian homeland hypothesis)]
  • A. indigenous peoples of Taiwan
    The indigenous peoples of Taiwan are the island’s original Austronesian-speaking inhabitants, comprising diverse ethnic groups with distinct languages, cultures, and histories predating Han Chinese settlement.
  • B. Formosan languages
    Formosan languages are a group of indigenous Austronesian languages spoken primarily by the native peoples of Taiwan and considered crucial for understanding the early diversification of the Austronesian language family.
  • C. Austronesian peoples
    Austronesian peoples are a widespread ethnolinguistic group originating from Taiwan and Island Southeast Asia whose seafaring descendants settled across the Pacific and Indian Oceans, including Polynesia, Micronesia, Melanesia, and Madagascar.
  • D. southern Taiwan
    Southern Taiwan is the lower region of Taiwan Island known for its warm climate, agriculture, and historic role in various uprisings and political movements.
  • E. Proto-Austronesian
    Proto-Austronesian is the reconstructed common ancestor of the Austronesian language family, from which languages such as Javanese, Tagalog, and Malay are derived.
  • 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: Taiwan (Austronesian homeland hypothesis)
Triple: [Malayo-Polynesian languages, historicalOrigin, Taiwan (Austronesian homeland hypothesis)]
Generated description
Taiwan (Austronesian homeland hypothesis) is a linguistic and archaeological theory proposing that the Austronesian language family originated in Taiwan before spreading across Island Southeast Asia and the Pacific.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taiwan (Austronesian homeland hypothesis)
Target entity description: Taiwan (Austronesian homeland hypothesis) is a linguistic and archaeological theory proposing that the Austronesian language family originated in Taiwan before spreading across Island Southeast Asia and the Pacific.
  • A. indigenous peoples of Taiwan
    The indigenous peoples of Taiwan are the island’s original Austronesian-speaking inhabitants, comprising diverse ethnic groups with distinct languages, cultures, and histories predating Han Chinese settlement.
  • B. Formosan languages chosen
    Formosan languages are a group of indigenous Austronesian languages spoken primarily by the native peoples of Taiwan and considered crucial for understanding the early diversification of the Austronesian language family.
  • C. Austronesian peoples
    Austronesian peoples are a widespread ethnolinguistic group originating from Taiwan and Island Southeast Asia whose seafaring descendants settled across the Pacific and Indian Oceans, including Polynesia, Micronesia, Melanesia, and Madagascar.
  • D. southern Taiwan
    Southern Taiwan is the lower region of Taiwan Island known for its warm climate, agriculture, and historic role in various uprisings and political movements.
  • E. Proto-Austronesian
    Proto-Austronesian is the reconstructed common ancestor of the Austronesian language family, from which languages such as Javanese, Tagalog, and Malay are derived.
  • F. None of above.

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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be233fd88190996faf4105c0b8d7 completed March 1, 2026, 10:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac832704c08190a1a73ebd90fa91b8 completed March 7, 2026, 7:57 p.m.
NEDg Description generation batch_69ac83add3608190be198ba153721d5c completed March 7, 2026, 7:59 p.m.
NED2 Entity disambiguation (via description) batch_69ac846e724081909696c8c44f2f9500 completed March 7, 2026, 8:02 p.m.
Created at: March 1, 2026, 7:47 p.m.