Triple

T10611375
Position Surface form Disambiguated ID Type / Status
Subject Sagaing E276015 entity
Predicate separatedFromByRiver P382 FINISHED
Object Mandalay E57185 NE FINISHED

How this triple was built (3 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: [Sagaing, separatedFromByRiver, Mandalay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandalay
Context triple: [Sagaing, separatedFromByRiver, 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. Pathein
    Pathein is a major city in Myanmar’s Ayeyarwady Region, known as a regional commercial hub and for its traditional handcrafted umbrellas.
  • E. 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.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: separatedFromByRiver
Context triple: [Sagaing, separatedFromByRiver, Mandalay]
  • A. separatedFromByLand
    Indicates that two entities are divided or kept apart from each other by an intervening landmass.
  • B. locatedAcrossRiverFrom chosen
    Indicates that one entity is situated on the opposite side of a river relative to another entity.
  • C. riverSeparatingFrom
    Indicates that one river branches off or diverges from another river, creating a separation between their flow paths.
  • D. locatedBetweenRiver
    Indicates that an entity is situated in the area or region between two segments or banks of a river, or between two rivers.
  • E. betweenRiver
    Indicates a spatial relationship where something is located in the area separating two rivers or lies in the intermediate region defined by them.
  • F. None of above.

Provenance (4 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6df5a1450819082ad445712fb7868 completed April 8, 2026, 11:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69d96b716a088190b84982f1a8173e0a completed April 10, 2026, 9:28 p.m.
PD Predicate disambiguation batch_69d6dd7a223c8190854409d76368f3e8 completed April 8, 2026, 10:58 p.m.
Created at: April 8, 2026, 7:33 p.m.