Triple

T10995926
Position Surface form Disambiguated ID Type / Status
Subject Unryu E259865 entity
Predicate hullNumber P3152 FINISHED
Object Unryu E259865 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: Unryu | Statement: [Unryu, hullNumber, Unryu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unryu
Context triple: [Unryu, hullNumber, Unryu]
  • A. Unryu chosen
    Unryu was a World War II-era Imperial Japanese Navy aircraft carrier that served in the Pacific Theater.
  • B. Yudachi
    Yudachi was an Imperial Japanese Navy destroyer of the Shiratsuyu class that served in World War II, notably participating in several major Pacific naval engagements before being sunk in 1942.
  • C. Tsurugi
    Tsurugi is a Japanese Shinkansen train service operating on the Hokuriku Shinkansen line, primarily providing all-stations shuttle connections between Toyama and Kanazawa.
  • D. Masaru
    Masaru is a Japanese given name commonly used for males and borne by various notable figures in fields such as technology, sports, and entertainment.
  • E. Tokomaru
    Tokomaru is a traditional Māori voyaging canoe (waka) associated with the Ngāpuhi iwi (tribe) in Aotearoa New Zealand.
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d795d6572c8190a47d68483863ad7a completed April 9, 2026, 12:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3452420c08190b9c91a9c8a807670 completed April 18, 2026, 8:47 a.m.
Created at: April 8, 2026, 9:24 p.m.