Triple

T12749294
Position Surface form Disambiguated ID Type / Status
Subject Shan language E304687 entity
Predicate hasDialects P4251 FINISHED
Object Tai Mao
Tai Mao is a dialect of the Shan language spoken by Tai ethnic communities, particularly in parts of Myanmar and neighboring regions.
E999416 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: Tai Mao | Statement: [Shan language, hasDialects, Tai Mao]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tai Mao
Context triple: [Shan language, hasDialects, Tai Mao]
  • A. Haad Yuan
    Haad Yuan is a small, secluded beach on Thailand’s Ko Pha Ngan island, known for its tranquil atmosphere, clear waters, and relaxed, off-the-beaten-path vibe.
  • B. Koh Tsu Koon
    Koh Tsu Koon is a Malaysian politician and former Chief Minister of Penang who later served as a federal minister.
  • C. Yukong
    Yukong was the former name of SK Energy, a major South Korean petroleum and energy company within the SK Group conglomerate.
  • D. Taizi
    Taizi is the traditional Chinese title for the designated heir apparent to the imperial throne.
  • E. T'ao
    T'ao is an alternative transliteration of the Chinese name "Tao," commonly used in older or Wade–Giles romanization systems.
  • 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: Tai Mao
Triple: [Shan language, hasDialects, Tai Mao]
Generated description
Tai Mao is a dialect of the Shan language spoken by Tai ethnic communities, particularly in parts of Myanmar and neighboring regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tai Mao
Target entity description: Tai Mao is a dialect of the Shan language spoken by Tai ethnic communities, particularly in parts of Myanmar and neighboring regions.
  • A. Haad Yuan
    Haad Yuan is a small, secluded beach on Thailand’s Ko Pha Ngan island, known for its tranquil atmosphere, clear waters, and relaxed, off-the-beaten-path vibe.
  • B. Koh Tsu Koon
    Koh Tsu Koon is a Malaysian politician and former Chief Minister of Penang who later served as a federal minister.
  • C. Yukong
    Yukong was the former name of SK Energy, a major South Korean petroleum and energy company within the SK Group conglomerate.
  • D. Taizi
    Taizi is the traditional Chinese title for the designated heir apparent to the imperial throne.
  • E. T'ao
    T'ao is an alternative transliteration of the Chinese name "Tao," commonly used in older or Wade–Giles romanization systems.
  • 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_69d7bdf1fcd081909ffb0e0d6fa3a07d completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96bd75f508190aaae0969f33d1523 completed April 10, 2026, 9:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69f67c964c508190b4d6a094b388280b completed May 2, 2026, 10:37 p.m.
NEDg Description generation batch_69f67d663fd08190a00b30a7ff260c70 completed May 2, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69f67e12b8148190958b63ba114d6221 completed May 2, 2026, 10:43 p.m.
Created at: April 9, 2026, 5:27 p.m.