Triple

T15984035
Position Surface form Disambiguated ID Type / Status
Subject Kachin Independence Organization E387645 entity
Predicate headquarters P62 FINISHED
Object Laiza
Laiza is a town in northern Myanmar near the Chinese border that serves as the main stronghold and de facto capital of the Kachin Independence Organization.
E1188144 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: Laiza | Statement: [Kachin Independence Organization, headquarters, Laiza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laiza
Context triple: [Kachin Independence Organization, headquarters, Laiza]
  • A. Sheyla
    Sheyla is a feminine given name, typically considered a variant of Sheila or Shayla and used in various cultures.
  • B. Laís
    Laís is a Brazilian given name notably borne by model Laís Ribeiro, recognized for her work with major international fashion brands.
  • C. Rosana
    Rosana is a Brazilian professional footballer known for her successful international career and contributions to top women’s clubs, including Avaldsnes IL.
  • D. Rosana
    Rosana is a municipality in the state of São Paulo, Brazil, known for hosting a campus of São Paulo State University (UNESP).
  • E. Marcela
    Marcela is one of the given names of Alexia Juliana Marcela Laurentien, a member of the Dutch royal family.
  • 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: Laiza
Triple: [Kachin Independence Organization, headquarters, Laiza]
Generated description
Laiza is a town in northern Myanmar near the Chinese border that serves as the main stronghold and de facto capital of the Kachin Independence Organization.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Laiza
Target entity description: Laiza is a town in northern Myanmar near the Chinese border that serves as the main stronghold and de facto capital of the Kachin Independence Organization.
  • A. Sheyla
    Sheyla is a feminine given name, typically considered a variant of Sheila or Shayla and used in various cultures.
  • B. Laís
    Laís is a Brazilian given name notably borne by model Laís Ribeiro, recognized for her work with major international fashion brands.
  • C. Rosana
    Rosana is a municipality in the state of São Paulo, Brazil, known for hosting a campus of São Paulo State University (UNESP).
  • D. Rosana
    Rosana is a Brazilian professional footballer known for her successful international career and contributions to top women’s clubs, including Avaldsnes IL.
  • E. Marcela
    Marcela is one of the given names of Alexia Juliana Marcela Laurentien, a member of the Dutch royal family.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15756d6488190ac35da00e96ce21d completed April 16, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3cdf7848190848e9081027dc027 completed May 9, 2026, 11:31 p.m.
NEDg Description generation batch_69ffc5669c1c81909bacf61c96cb7816 completed May 9, 2026, 11:38 p.m.
NED2 Entity disambiguation (via description) batch_69ffc5c7db1c8190b4e1de6f6e3ce8a0 completed May 9, 2026, 11:39 p.m.
Created at: April 10, 2026, 4:54 a.m.