Triple

T21748536
Position Surface form Disambiguated ID Type / Status
Subject Tonghua E536849 entity
Predicate locatedOnRiver P165 FINISHED
Object Yalu 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: Yalu River | Statement: [Tonghua, locatedOnRiver, Yalu River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yalu River
Context triple: [Tonghua, locatedOnRiver, Yalu River]
  • A. Yalu River chosen
    The Yalu River is a major East Asian river that forms much of the border between North Korea and China and has long held strategic and historical significance in the region.
  • B. Tumen-gang River
    Tumen-gang River is a border river in Northeast Asia that flows between China, North Korea, and Russia before emptying into the Sea of Japan.
  • C. Changjin River
    The Changjin River is a river in northeastern North Korea known for flowing through the mountainous region near the Chosin Reservoir, a key site in the Korean War.
  • D. Ch'ongch'on River
    The Ch'ongch'on River is a major river in northwestern North Korea that gained historical significance as the site of a pivotal battle during the Korean War.
  • E. Yi River
    The Yi River is a significant river in Shandong Province, China, known for flowing through the city of Linyi and its surrounding agricultural and historical regions.
  • 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_69e0c46eab808190b848242d63a17c47 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f01a77e19c81909bf26f96aa41a7ce completed April 28, 2026, 2:24 a.m.
Created at: April 16, 2026, 6:50 p.m.