Triple

T1695734
Position Surface form Disambiguated ID Type / Status
Subject Shiyan E36652 entity
Predicate locatedOnRiver P165 FINISHED
Object Han River E54414 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: Han River | Statement: [Shiyan, locatedOnRiver, Han River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Han River
Context triple: [Shiyan, locatedOnRiver, Han River]
  • A. Han River chosen
    The Han River is a major tributary of the Yangtze River in central China, flowing through Hubei province and the city of Wuhan.
  • B. Han River
    The Han River is a major river in South Korea that flows through the capital city of Seoul and serves as a central geographic and cultural landmark.
  • C. Han River
    The Han River is a central waterway in Da Nang, Vietnam, known for its scenic riverside skyline and iconic bridges such as the Dragon Bridge and Han River Bridge.
  • D. Fox River
    The Fox River is a Midwestern U.S. river that flows through Wisconsin and Illinois, supporting numerous communities and ecosystems along its course.
  • E. Illinois River
    The Illinois River is a principal waterway in the U.S. state of Illinois that serves as a key tributary of the Mississippi River and an important route for transportation, commerce, and recreation.
  • 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_69a886163dec8190859c514232a37a05 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62b645a081909dafdf7a32f2a389 completed March 6, 2026, 5:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfb96d12481908f8d7d5c9f1f103f completed March 8, 2026, 10:43 p.m.
Created at: March 4, 2026, 7:30 p.m.