Triple

T13594210
Position Surface form Disambiguated ID Type / Status
Subject Type 30 bayonet E324771 entity
Predicate militaryDesignation P7137 FINISHED
Object Type 30
Type 30 is a Japanese military bayonet model historically issued with Arisaka rifles in the early 20th century.
E1049530 NE FINISHED

How this triple was built (4 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: Type 30 | Statement: [Type 30 bayonet, militaryDesignation, Type 30]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Type 30
Context triple: [Type 30 bayonet, militaryDesignation, Type 30]
  • A. S30
    S30 is the pennant number of HMS Vigilant, a Royal Navy Vanguard-class nuclear-powered ballistic missile submarine.
  • B. R30
    R30 is a regional commuter rail line within the Rodalies de Catalunya network serving the Barcelona metropolitan area and surrounding regions.
  • C. MIB30
    MIB30 was a former benchmark stock market index of the Italian equity market, comprising 30 of the most liquid and capitalized companies listed on the Borsa Italiana.
  • D. M30
    M30 is a globular star cluster in the constellation Capricornus, notable for its dense core and great age.
  • E. The 305
    The 305 is a nickname commonly used to refer to Miami, Florida, derived from its original area code.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Type 30
Triple: [Type 30 bayonet, militaryDesignation, Type 30]
Generated description
Type 30 is a Japanese military bayonet model historically issued with Arisaka rifles in the early 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Type 30
Target entity description: Type 30 is a Japanese military bayonet model historically issued with Arisaka rifles in the early 20th century.
  • A. S30
    S30 is the pennant number of HMS Vigilant, a Royal Navy Vanguard-class nuclear-powered ballistic missile submarine.
  • B. R30
    R30 is a regional commuter rail line within the Rodalies de Catalunya network serving the Barcelona metropolitan area and surrounding regions.
  • C. MIB30
    MIB30 was a former benchmark stock market index of the Italian equity market, comprising 30 of the most liquid and capitalized companies listed on the Borsa Italiana.
  • D. M30
    M30 is a globular star cluster in the constellation Capricornus, notable for its dense core and great age.
  • E. The 305
    The 305 is a nickname commonly used to refer to Miami, Florida, derived from its original area code.
  • F. None of above. chosen

Provenance (5 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_69d80769eaf081909d82f44e484d6113 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb057f1c881909a3bb77c659a724a completed April 12, 2026, 2:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bc762a08190b5d29cef9923da84 completed May 3, 2026, 3:37 p.m.
NEDg Description generation batch_69f77643b0348190962bf23a9857edbe completed May 3, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_69f77923fd1481908af251a1dcbcf441 completed May 3, 2026, 4:34 p.m.
Created at: April 9, 2026, 9:49 p.m.