Triple

T6839896
Position Surface form Disambiguated ID Type / Status
Subject Anzac-class frigate E157543 entity
Predicate numberBuiltFor P2091 FINISHED
Object 8 for Royal Australian Navy LITERAL 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: 8 for Royal Australian Navy | Statement: [Anzac-class frigate, numberBuiltFor, 8 for Royal Australian Navy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: numberBuiltFor
Context triple: [Anzac-class frigate, numberBuiltFor, 8 for Royal Australian Navy]
  • A. numberBuilt chosen
    Indicates the total count of items or structures that have been constructed or produced.
  • B. isBuiltFor
    Indicates that one entity is specifically designed, intended, or optimized to serve, support, or accommodate another entity or purpose.
  • C. modelNumber
    Indicates that one entity is the specific model identifier or code assigned to another entity (such as a product or device).
  • D. builtOn
    Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
  • E. hasPartNumber
    Indicates that one entity is assigned or associated with a specific part number used to identify it within a catalog, system, or inventory.
  • F. None of above.

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_69c6882c53608190b99aebef079b23bd completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d6b2ee248190991c3e827be75bb7 completed March 27, 2026, 7:12 p.m.
PD Predicate disambiguation batch_69c6d09f90648190bc0a462c7d59de1b completed March 27, 2026, 6:46 p.m.
Created at: March 27, 2026, 2:19 p.m.