Triple

T12594603
Position Surface form Disambiguated ID Type / Status
Subject Mount Tsukuba E300701 entity
Predicate hasShrine P15258 FINISHED
Object Tsukuba Shrine E1123896 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: Tsukuba Shrine | Statement: [Mount Tsukuba, hasShrine, Tsukuba Shrine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tsukuba Shrine
Context triple: [Mount Tsukuba, hasShrine, Tsukuba Shrine]
  • A. Tsukuba Shrine chosen
    Tsukuba Shrine is a historic Shinto shrine in Ibaraki Prefecture, Japan, revered for its mountain worship and scenic location on the slopes of Mount Tsukuba.
  • B. Tsukubusuma Shrine
    Tsukubusuma Shrine is a historic Shinto shrine on Chikubu Island in Japan’s Lake Biwa, revered for its scenic setting and long-standing religious significance.
  • C. Ebara Shrine
    Ebara Shrine is a historic Shinto shrine located in Tokyo’s Shinagawa ward, known for serving as a local spiritual and cultural center.
  • D. Yaegaki Shrine
    Yaegaki Shrine is a Shinto shrine in Matsue, Japan, famed for its association with the deity Susanoo-no-Mikoto and popular as a place to pray for love and marriage.
  • E. Kifune Shrine
    Kifune Shrine is an ancient Shinto shrine in the mountains north of Kyoto, renowned for its water deity worship, atmospheric lantern-lined approach, and picturesque riverside setting.
  • 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_69d7bdea2ca881908f379526c13b1145 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954cde3c0819094e74413d6dcf548 completed April 10, 2026, 7:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b366470819093a74828e2a85116 completed May 8, 2026, 11:01 p.m.
Created at: April 9, 2026, 5:08 p.m.