Triple

T6184395
Position Surface form Disambiguated ID Type / Status
Subject Saisiyat language E138019 entity
Predicate hasDialect P4251 FINISHED
Object Taai dialect
The Taai dialect is a regional variety of the Saisiyat language spoken by the indigenous Saisiyat people of Taiwan.
 E574285 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: Taai dialect | Statement: [Saisiyat language, hasDialect, Taai dialect]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Taai dialect
Context triple: [Saisiyat language, hasDialect, Taai dialect]
  • A. Chaoshan dialect
    The Chaoshan dialect, also known as Teochew, is a Southern Min Chinese variety spoken primarily in the Chaoshan region of eastern Guangdong and by large overseas Chinese communities in Southeast Asia and beyond.
  • B. Hkaku dialect
    Hkaku dialect is a regional variety of the Jingpo language spoken by Jingpo communities in parts of Myanmar and neighboring areas.
  • C. Kikai dialect
    The Kikai dialect is a regional variety of the Amami language spoken on Kikai Island in Japan’s Ryukyu archipelago.
  • D. Bangang dialect
    The Bangang dialect is a regional variety of the Ghomalaʼ language spoken by the Bangang community in western Cameroon.
  • E. Tigapanah dialect
    The Tigapanah dialect is a regional variety of the Karo Batak language spoken by Karo communities in and around the Tigapanah area of North Sumatra, 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: Taai dialect
Triple: [Saisiyat language, hasDialect, Taai dialect]
Generated description
The Taai dialect is a regional variety of the Saisiyat language spoken by the indigenous Saisiyat people of Taiwan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Taai dialect
Target entity description: The Taai dialect is a regional variety of the Saisiyat language spoken by the indigenous Saisiyat people of Taiwan.
  • A. Chaoshan dialect
    The Chaoshan dialect, also known as Teochew, is a Southern Min Chinese variety spoken primarily in the Chaoshan region of eastern Guangdong and by large overseas Chinese communities in Southeast Asia and beyond.
  • B. Hkaku dialect
    Hkaku dialect is a regional variety of the Jingpo language spoken by Jingpo communities in parts of Myanmar and neighboring areas.
  • C. Kikai dialect
    The Kikai dialect is a regional variety of the Amami language spoken on Kikai Island in Japan’s Ryukyu archipelago.
  • D. Bangang dialect
    The Bangang dialect is a regional variety of the Ghomalaʼ language spoken by the Bangang community in western Cameroon.
  • E. Tigapanah dialect
    The Tigapanah dialect is a regional variety of the Karo Batak language spoken by Karo communities in and around the Tigapanah area of North Sumatra, 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c061020d148190ae2edf2b363f1e24 completed March 22, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141c6b5888190983bff620c7663cc completed March 23, 2026, 1:36 p.m.
NEDg Description generation batch_69c1472997d081909266b0e64fdbfe96 completed March 23, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69c147b5214c819082c20480965842be completed March 23, 2026, 2:01 p.m.
Created at: March 22, 2026, 4:19 p.m.