Triple

T9504115
Position Surface form Disambiguated ID Type / Status
Subject Yangon River E229218 entity
Predicate hasPort P35 FINISHED
Object Port of Yangon E218963 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: Port of Yangon | Statement: [Yangon River, hasPort, Port of Yangon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port of Yangon
Context triple: [Yangon River, hasPort, Port of Yangon]
  • A. Port of Yangon chosen
    The Port of Yangon is Myanmar’s principal seaport and trade gateway, handling the majority of the country’s maritime cargo and connecting it to regional and global shipping routes.
  • B. Mongla Port
    Mongla Port is Bangladesh’s second-largest seaport, serving as a key maritime gateway in the country’s southwest region.
  • C. Myanma Port Authority
    The Myanma Port Authority is the state-owned agency responsible for managing and regulating Myanmar’s major seaports and maritime infrastructure.
  • D. Dawei
    Dawei are an ethnic group from southern Myanmar, known for their distinct language and culture centered around the Tanintharyi coastal region.
  • E. Cua Lo Port
    Cua Lo Port is a coastal seaport in north-central Vietnam that serves as a key maritime gateway for Nghe An Province and the surrounding 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_69ca847611c48190a28c028644198c75 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9840148081908df237f212b62e67 completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d13a17abac8190823cec6b8328bc96 completed April 4, 2026, 4:19 p.m.
Created at: March 30, 2026, 7:57 p.m.