Triple

T7743396
Position Surface form Disambiguated ID Type / Status
Subject Karenni State E175563 entity
Predicate hasCapital P204 FINISHED
Object Loikaw
Loikaw is the principal urban center and administrative hub of Myanmar’s Kayah (Karenni) State, known for its surrounding hills, ethnic diversity, and traditional culture.
E685692 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: Loikaw | Statement: [Karenni State, hasCapital, Loikaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Loikaw
Context triple: [Karenni State, hasCapital, Loikaw]
  • A. Leuwiliang
    Leuwiliang is a district-level area in West Java, Indonesia, known as part of the greater Bogor region.
  • B. Lien Bang
    Lien Bang is a township that serves as the administrative and political center of Y Yen District in Vietnam.
  • C. Liguo
    Liguo is a Chinese given name commonly used for males and borne by various individuals across different fields.
  • D. Wayao
    Wayao is an alternative name for the Yao, an ethnic group found primarily in parts of China and Southeast Asia known for their distinct cultural traditions and languages.
  • E. Laoang
    Laoang is a coastal municipality in the province of Northern Samar in the Philippines, known for its island landscapes and fishing communities.
  • 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: Loikaw
Triple: [Karenni State, hasCapital, Loikaw]
Generated description
Loikaw is the principal urban center and administrative hub of Myanmar’s Kayah (Karenni) State, known for its surrounding hills, ethnic diversity, and traditional culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Loikaw
Target entity description: Loikaw is the principal urban center and administrative hub of Myanmar’s Kayah (Karenni) State, known for its surrounding hills, ethnic diversity, and traditional culture.
  • A. Leuwiliang
    Leuwiliang is a district-level area in West Java, Indonesia, known as part of the greater Bogor region.
  • B. Lien Bang
    Lien Bang is a township that serves as the administrative and political center of Y Yen District in Vietnam.
  • C. Liguo
    Liguo is a Chinese given name commonly used for males and borne by various individuals across different fields.
  • D. Wayao
    Wayao is an alternative name for the Yao, an ethnic group found primarily in parts of China and Southeast Asia known for their distinct cultural traditions and languages.
  • E. Laoang
    Laoang is a coastal municipality in the province of Northern Samar in the Philippines, known for its island landscapes and fishing communities.
  • 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_69c6995f9c60819092e386192bd63c6f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c70388d58081909aad2c03b4501e78 completed March 27, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be48d61c8190aba1e5f23d7cb1be completed March 29, 2026, 5:53 a.m.
NEDg Description generation batch_69c8bf664390819093c2381ff0f8aaca completed March 29, 2026, 5:57 a.m.
NED2 Entity disambiguation (via description) batch_69c8bff4965881909a341db7d234632a completed March 29, 2026, 6 a.m.
Created at: March 27, 2026, 4:07 p.m.