Triple

T6698746
Position Surface form Disambiguated ID Type / Status
Subject Yamato River E152820 entity
Predicate hasTributary P415 FINISHED
Object Saho River
The Saho River is a Japanese river in the Kansai region that forms part of the Yamato River system.
 E731587 NE FINISHED

How this triple was built (4 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: Saho River | Statement: [Yamato River, hasTributary, Saho River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saho River
Context triple: [Yamato River, hasTributary, Saho River]
  • A. Sonai River
    The Sonai River is a tributary waterway in northeastern India that feeds into the larger Barak River system.
  • B. Ichu River
    The Ichu River is a waterway in the central highlands of Peru that flows through the Huancavelica region, contributing to its Andean landscape and local ecosystems.
  • C. Gomai River
    The Gomai River is a smaller river in western India that feeds into the larger Tapti River system.
  • D. Futun River
    The Futun River is a significant waterway in Fujian, China, known for feeding into the Min River and supporting regional transport, agriculture, and ecosystems.
  • E. Segama River
    The Segama River is one of the longest and most significant rivers in the Malaysian state of Sabah, known for flowing through rich rainforest and wildlife habitats in eastern Borneo.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Saho River
Triple: [Yamato River, hasTributary, Saho River]
Generated description
The Saho River is a Japanese river in the Kansai region that forms part of the Yamato River system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saho River
Target entity description: The Saho River is a Japanese river in the Kansai region that forms part of the Yamato River system.
  • A. Sonai River
    The Sonai River is a tributary waterway in northeastern India that feeds into the larger Barak River system.
  • B. Ichu River
    The Ichu River is a waterway in the central highlands of Peru that flows through the Huancavelica region, contributing to its Andean landscape and local ecosystems.
  • C. Gomai River
    The Gomai River is a smaller river in western India that feeds into the larger Tapti River system.
  • D. Futun River
    The Futun River is a significant waterway in Fujian, China, known for feeding into the Min River and supporting regional transport, agriculture, and ecosystems.
  • E. Segama River
    The Segama River is one of the longest and most significant rivers in the Malaysian state of Sabah, known for flowing through rich rainforest and wildlife habitats in eastern Borneo.
  • F. None of above. chosen

Provenance (5 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_69c68807adbc8190b8632df42b39eda0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d0a6082c819097a4301538399f59 completed March 27, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce019fb0cc81908a24b0e39110325d completed April 2, 2026, 5:41 a.m.
NEDg Description generation batch_69ce064211e48190b558d4355be659ba completed April 2, 2026, 6:01 a.m.
NED2 Entity disambiguation (via description) batch_69ce07a390048190ac26a7e3d3d561e0 completed April 2, 2026, 6:07 a.m.
Created at: March 27, 2026, 2:05 p.m.