Triple

T13037706
Position Surface form Disambiguated ID Type / Status
Subject Sanyō Shinkansen E326605 entity
Predicate serviceType P87 FINISHED
Object Hikari E306033 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: Hikari | Statement: [Sanyō Shinkansen, serviceType, Hikari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hikari
Context triple: [Sanyō Shinkansen, serviceType, Hikari]
  • A. Hikari chosen
    Hikari is a high-speed Shinkansen train service in Japan that operates on the Tokaido and Sanyo Shinkansen lines, offering fast intercity travel with fewer stops than local services.
  • B. Hikari
    Hikari is a Wayland compositor for FreeBSD that focuses on simplicity, performance, and tiling window management, built on the wlroots library.
  • C. Hikari
    Hikari is a Japanese given name commonly used for both males and females, meaning "light" in Japanese.
  • D. Hizaori
    Hizaori is the former name of Asaka, a city located in Saitama Prefecture, Japan.
  • E. Hoori
    Hoori is a deity in Japanese mythology, known as a divine hunter and ancestor of Japan’s imperial line.
  • 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_69d8076cc45c81908123123f43e69266 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d9804b743c8190810dc5c14bc6d912 completed April 10, 2026, 10:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbd12eec81908ad5dae638c2210e completed May 3, 2026, 4:15 a.m.
Created at: April 9, 2026, 8:55 p.m.