Triple

T38183728
Position Surface form Disambiguated ID Type / Status
Subject Iwakuni E1005245 entity
Predicate formerDomainCenter P201752 FINISHED
Object Iwakuni Domain NE NERFINISHED

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: Iwakuni Domain | Statement: [Iwakuni, formerDomainCenter, Iwakuni Domain]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerDomainCenter
Context triple: [Iwakuni, formerDomainCenter, Iwakuni Domain]
  • A. laterDomainCenter
    Indicates that one domain center occurs at a later time or stage than another domain center within a given context.
  • B. formerDomain
    Indicates that one entity was previously the domain or area of control, influence, or ownership of another entity, but no longer is.
  • C. domainCenter
    Indicates that something is located at or serves as the central point or core area of a specified domain or region.
  • D. formerAdminCenter chosen
    Indicates that an entity once served as an administrative center for another entity but no longer holds that status.
  • E. publicDomain
    Indicates that a work or resource is not protected by intellectual property rights and is freely available for anyone to use, copy, modify, and distribute without restriction.
  • 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_69f76dbc22c481908139b694ffde7a0c completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_6a013a251b4081908b43d85dd95586c5 completed May 11, 2026, 2:08 a.m.
PD Predicate disambiguation batch_6a0137e4ea988190812173a5ff044098 completed May 11, 2026, 1:59 a.m.
Created at: May 3, 2026, 4:29 p.m.