Triple

T9842093
Position Surface form Disambiguated ID Type / Status
Subject Mandalay Region E239251 entity
Predicate containsCity P294 FINISHED
Object Kyaukse
Kyaukse is a town in central Myanmar known for its fertile agricultural lands and historic Buddhist pagodas, located south of Mandalay in the Mandalay Region.
E825357 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: Kyaukse | Statement: [Mandalay Region, containsCity, Kyaukse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kyaukse
Context triple: [Mandalay Region, containsCity, Kyaukse]
  • A. Kandawgyi
    Kandawgyi is a prominent artificial lake and scenic landmark in central Yangon, Myanmar, known for its park, boardwalks, and views of the Shwedagon Pagoda.
  • B. Kyaikto
    Kyaikto is a town in southeastern Myanmar best known as the gateway to the famous Golden Rock (Kyaiktiyo Pagoda) pilgrimage site.
  • C. Paung
    Paung is a town in southeastern Myanmar that serves as a local center within Mon State.
  • D. Maung
    Maung is a Burmese surname commonly used in Myanmar and among the Burmese diaspora.
  • E. Pyinbya
    Pyinbya was an early Burmese king traditionally credited with establishing Bagan as a fortified city, laying the foundations for the Pagan Kingdom that unified much of present-day Myanmar.
  • 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: Kyaukse
Triple: [Mandalay Region, containsCity, Kyaukse]
Generated description
Kyaukse is a town in central Myanmar known for its fertile agricultural lands and historic Buddhist pagodas, located south of Mandalay in the Mandalay Region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kyaukse
Target entity description: Kyaukse is a town in central Myanmar known for its fertile agricultural lands and historic Buddhist pagodas, located south of Mandalay in the Mandalay Region.
  • A. Kandawgyi
    Kandawgyi is a prominent artificial lake and scenic landmark in central Yangon, Myanmar, known for its park, boardwalks, and views of the Shwedagon Pagoda.
  • B. Kyaikto
    Kyaikto is a town in southeastern Myanmar best known as the gateway to the famous Golden Rock (Kyaiktiyo Pagoda) pilgrimage site.
  • C. Paung
    Paung is a town in southeastern Myanmar that serves as a local center within Mon State.
  • D. Maung
    Maung is a Burmese surname commonly used in Myanmar and among the Burmese diaspora.
  • E. Pyinbya
    Pyinbya was an early Burmese king traditionally credited with establishing Bagan as a fortified city, laying the foundations for the Pagan Kingdom that unified much of present-day Myanmar.
  • 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_69ca84e3f0c48190ada72a65ebd50efd completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb34e3420819084bb31170e643cd0 completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5d9673c8190ada27bef9220798d completed April 5, 2026, 3:24 a.m.
NEDg Description generation batch_69d1d6815e28819081788393cda63bc0 completed April 5, 2026, 3:26 a.m.
NED2 Entity disambiguation (via description) batch_69d1d74e7a148190a9470745bfd7ad42 completed April 5, 2026, 3:30 a.m.
Created at: March 30, 2026, 8:33 p.m.