Triple

T31224812
Position Surface form Disambiguated ID Type / Status
Subject Cold War-era Royal Navy E796108 entity
Predicate notableSSNClass P62791 FINISHED
Object Valiant-class submarine E1136598 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: Valiant-class submarine | Statement: [Cold War-era Royal Navy, notableSSNClass, Valiant-class submarine]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableSSNClass
Context triple: [Cold War-era Royal Navy, notableSSNClass, Valiant-class submarine]
  • A. notableClass chosen
    Indicates that an entity belongs to a particularly important, distinguished, or otherwise noteworthy class or category within a given classification system.
  • B. notableStandard
    Indicates that one entity is a widely recognized or influential standard that the other entity is associated with or exemplifies.
  • C. notableDisplay
    Indicates that something is prominently or distinctively presented in a way that draws special attention or recognition.
  • D. notableTypeOf
    Indicates that one entity is a particularly prominent, well-known, or exemplary instance or subtype of another entity.
  • E. notableState
    Indicates that an entity is significantly associated with, recognized in, or prominently linked to a particular state (such as a U.S. state or similar regional jurisdiction).
  • F. None of above.

Provenance (4 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_69f224da98f88190ab32f690cce5d303 completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_6a037c876524819098545e6037d3107d completed May 12, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2b2d6281108190926f170507de3532 completed June 11, 2026, 9:49 p.m.
PD Predicate disambiguation batch_6a0379e5174c8190a0bdde7e381b7624 completed May 12, 2026, 7:05 p.m.
Created at: April 29, 2026, 9:10 p.m.