Triple

T8858387
Position Surface form Disambiguated ID Type / Status
Subject Awaji E210820 entity
Predicate locatedSouthOf P9676 FINISHED
Object Akashi E194040 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: Akashi | Statement: [Awaji, locatedSouthOf, Akashi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akashi
Context triple: [Awaji, locatedSouthOf, Akashi]
  • A. Akashi chosen
    Akashi is a coastal city in western Japan known for its historic castle, views of the Akashi Kaikyō Strait, and its specialty dish akashiyaki.
  • B. Kanmon Kaikyo
    Kanmon Kaikyo is the narrow sea channel separating Japan’s Honshu and Kyushu islands, serving as a vital maritime passage and transport link between the Sea of Japan and the Seto Inland Sea.
  • C. Ōjin
    Ōjin is a semi-legendary early Japanese emperor traditionally regarded as the 15th ruler of Japan and later venerated as the Shinto war deity Hachiman.
  • D. Tenryu
    Tenryu is the original name of Japan's famed Blue Impulse aerobatic demonstration team.
  • E. Shinkyō
    Shinkyō is the Japanese name for Hsinking, the former capital city of the Japanese puppet state Manchukuo in northeastern China during the early 20th century.
  • 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_69ca838bbddc8190ab546d737e5d350f completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60e3b62c8190bf779e7e1db767f6 completed April 1, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc1c3c6c08190b51ea5e9cf7085e9 completed April 3, 2026, 1:33 p.m.
Created at: March 30, 2026, 6:50 p.m.