Triple

T16971634
Position Surface form Disambiguated ID Type / Status
Subject Jingo-ji E411697 entity
Predicate locatedIn P40 FINISHED
Object Ukyo-ku, Kyoto E949548 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: Ukyo-ku, Kyoto | Statement: [Jingo-ji, locatedIn, Ukyo-ku, Kyoto]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ukyo-ku, Kyoto
Context triple: [Jingo-ji, locatedIn, Ukyo-ku, Kyoto]
  • A. Ukyo-ku, Kyoto chosen
    Ukyo-ku, Kyoto is one of Kyoto City's western wards, known for its historic temples, traditional streets, and scenic areas such as Arashiyama.
  • B. Nakagyō-ku, Kyoto
    Nakagyō-ku, Kyoto is a central ward of Kyoto City known for its historic sites, traditional streetscapes, and role as a cultural and commercial hub.
  • C. Kamigyo-ku, Kyoto
    Kamigyo-ku, Kyoto is a central ward of Kyoto City known for its historic neighborhoods, traditional culture, and many important temples and shrines.
  • D. Sakyo-ku, Kyoto
    Sakyo-ku, Kyoto is a northeastern ward of Kyoto City known for its major universities, historic temples, and scenic natural areas including parts of the Higashiyama and Kitayama mountains.
  • E. Minami-ku, Kyoto
    Minami-ku, Kyoto is one of Kyoto City's southern wards, known for its mix of historic temples, industrial areas, and residential neighborhoods.
  • 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_69d886ca8f348190812768ea8d5055ce completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d0ad04ac81909a11b45be567613a completed April 18, 2026, 6:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00d471d4248190acf40b6c11926a65 completed May 10, 2026, 6:54 p.m.
Created at: April 10, 2026, 5:31 a.m.