Triple

T3554628
Position Surface form Disambiguated ID Type / Status
Subject Shan States E75189 entity
Predicate formerCapital P3417 FINISHED
Object Mandalay E57185 NE FINISHED

How this triple was built (2 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: Mandalay | Statement: [Shan States, formerCapital, Mandalay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandalay
Context triple: [Shan States, formerCapital, Mandalay]
  • A. Mandalay chosen
    Mandalay is a major cultural and economic center in central Myanmar, historically known as the last royal capital of the Burmese kingdom.
  • B. Yangon
    Yangon is Myanmar’s largest city and former capital, known as a major commercial hub featuring a mix of colonial architecture and prominent Buddhist landmarks like the Shwedagon Pagoda.
  • C. Lashio
    Lashio is a key town in northern Myanmar that historically served as an important transport and trade hub, particularly during World War II as the inland gateway to the Burma Road.
  • D. Amarapura
    Amarapura is a former royal city in Myanmar renowned for its role as an early Burmese capital and for landmarks such as the U Bein Bridge.
  • E. Taunggyi
    Taunggyi is a major city in eastern Myanmar known as an administrative, cultural, and commercial center in the Shan region.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad85d33c6c819081d5ac1df13b5680 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc05549d88190acdebdd542ea1a67 completed March 8, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bb95bcc88190abf1ea2efc30faeb completed March 13, 2026, 7:24 a.m.
Created at: March 8, 2026, 3:20 p.m.