Triple

T1925360
Position Surface form Disambiguated ID Type / Status
Subject Yodo River E40816 entity
Predicate hasTributary P415 FINISHED
Object Uji River E426911 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: Uji River | Statement: [Yodo River, hasTributary, Uji River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uji River
Context triple: [Yodo River, hasTributary, Uji River]
  • A. Uji River chosen
    The Uji River is a scenic waterway in Japan’s Kyoto Prefecture, famed for its historic tea-producing town of Uji and its cultural and literary significance.
  • B. Situk River
    The Situk River is a renowned Alaskan river famous for its pristine waters and exceptional wild salmon and steelhead fishing.
  • C. Siang River
    The Siang River is a major river in northeastern India that forms the upper course of the Brahmaputra as it flows from Tibet into Arunachal Pradesh.
  • D. Plenty River
    The Plenty River is a waterway in Victoria, Australia, that flows through Melbourne’s northeastern suburbs before joining the Yarra River.
  • E. Mutirikwi River
    Mutirikwi River is a river in southeastern Zimbabwe that flows near the ancient stone city of Great Zimbabwe and feeds Lake Mutirikwi.
  • 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_69a8864711648190b07bed24ed76258e completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb260da088190ac53bfc9437e112b completed March 7, 2026, 5:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69b5c6c1bb08819086668e6c1f0cce03 completed March 14, 2026, 8:36 p.m.
Created at: March 4, 2026, 7:35 p.m.