Triple

T19193819
Position Surface form Disambiguated ID Type / Status
Subject Stung Treng E469912 entity
Predicate locatedOnRiver P165 FINISHED
Object Sekong River NE NERFINISHED

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: Sekong River | Statement: [Stung Treng, locatedOnRiver, Sekong River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sekong River
Context triple: [Stung Treng, locatedOnRiver, Sekong River]
  • A. Sekong River chosen
    The Sekong River is a significant transboundary river in Southeast Asia that flows through Laos, Vietnam, and Cambodia before joining the Mekong.
  • B. Namtha River
    The Namtha River is a significant waterway in northern Laos that flows through Luang Namtha Province, supporting local agriculture, transport, and ecotourism.
  • C. Nam Non River
    The Nam Non River is a tributary waterway in Southeast Asia that feeds into the larger Ma River system.
  • D. Namoi River
    The Namoi River is a major inland river in New South Wales, Australia, flowing through rich agricultural regions before joining the Barwon–Darling river system.
  • E. Nhue River
    The Nhue River is a significant waterway in northern Vietnam that flows through the Red River Delta region, supporting agriculture, drainage, and daily life in provinces such as Ha Nam.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a409948190a17aa28a6e9c8844 completed April 20, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:07 p.m.