Triple

T9939454
Position Surface form Disambiguated ID Type / Status
Subject Akashi E194040 entity
Predicate knownFor P22 FINISHED
Object akashiyaki E3088 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: akashiyaki | Statement: [Akashi, knownFor, akashiyaki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: akashiyaki
Context triple: [Akashi, knownFor, akashiyaki]
  • A. Oshiage
    Oshiage is a district in Sumida, Tokyo, best known as the location of the Tokyo Skytree and its surrounding commercial complex.
  • B. Kanjizai
    Kanjizai is another name for Kannon, the bodhisattva of compassion in Buddhist tradition.
  • C. Okonomiyaki chosen
    Okonomiyaki is a savory Japanese pancake made from a batter of flour, cabbage, and various mix-ins, typically grilled and topped with a rich sauce, mayonnaise, and bonito flakes.
  • D. Nihon Shuwa
    Nihon Shuwa is the primary sign language used by the Deaf community in Japan, with its own distinct grammar, vocabulary, and cultural history.
  • E. Fukuchiyama yakisoba
    Fukuchiyama yakisoba is a regional style of Japanese fried noodles from Fukuchiyama, Kyoto Prefecture, known for its distinctive local ingredients and flavoring.
  • 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_69ca82e409348190a393777356b80a2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5e819e08190967b799fd236749e completed April 2, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228fdb8e48190808702d48470395a completed April 5, 2026, 9:18 a.m.
Created at: March 30, 2026, 8:44 p.m.