Triple

T417155
Position Surface form Disambiguated ID Type / Status
Subject Marshal Admiral of the Imperial Japanese Navy E8018 entity
Predicate promotionCriteria P216 FINISHED
Object exceptional merit 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: exceptional merit | Statement: [Marshal Admiral of the Imperial Japanese Navy, promotionCriteria, exceptional merit]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: promotionCriteria
Context triple: [Marshal Admiral of the Imperial Japanese Navy, promotionCriteria, exceptional merit]
  • A. awardCriteria chosen
    Indicates the standards or conditions used to determine eligibility for receiving an award or recognition.
  • B. promotionFrom
    Indicates that an entity has been elevated in position, rank, or status from a specified prior role or level.
  • C. selectionCriteria
    Indicates the conditions or rules used to choose certain entities from a larger set.
  • D. promotionTo
    Indicates that one entity is elevated or advanced to a higher rank, position, or status relative to another entity or context.
  • E. primaryCriterion
    Indicates that one factor is designated as the main or most important basis for a decision, judgment, or selection among alternatives.
  • 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_69a2e7f1d1bc81909cf2dc9754a3c334 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2eebde1d881908fb212bfba9d7c67 completed Feb. 28, 2026, 1:33 p.m.
PD Predicate disambiguation batch_69a2edd1ca148190a66bd8c5aad867d5 completed Feb. 28, 2026, 1:29 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.