Triple

T1509741
Position Surface form Disambiguated ID Type / Status
Subject Prince Asaka Yasuhiko E33985 entity
Predicate lostImperialStatus P20623 FINISHED
Object 1947 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: 1947 | Statement: [Prince Asaka Yasuhiko, lostImperialStatus, 1947]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: lostImperialStatus
Context triple: [Prince Asaka Yasuhiko, lostImperialStatus, 1947]
  • A. reasonForLossOfImperialStatus
    Indicates the cause or circumstance that led to an entity losing its imperial status.
  • B. lostImperialFamilyMembership chosen
    Indicates that an entity that once belonged to an imperial family has ceased to hold that imperial family membership or status.
  • C. lostThroneTo
    Indicates that one entity was previously in possession of a throne or rulership but was defeated or displaced so that another entity took that throne instead.
  • D. lostMostPowersTo
    Indicates that one entity has been deprived of the majority of its powers, abilities, or authority as a result of another entity’s actions or influence.
  • E. lostPresidency
    Indicates that an entity who previously held a presidency position has ceased to hold that office, typically as a result of an election or other loss of power.
  • 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_69a885f352a4819099b24ff15489dede completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a8e2dd93dc8190a78443900e8d5564 completed March 5, 2026, 1:56 a.m.
PD Predicate disambiguation batch_69a88728c150819095cdcdbfcabf4249 completed March 4, 2026, 7:25 p.m.
Created at: March 4, 2026, 7:24 p.m.