Triple

T20210190
Position Surface form Disambiguated ID Type / Status
Subject Dementor’s Kiss E493468 entity
Predicate legalStatusInWizardingWorld P2250 FINISHED
Object legal punishment for certain crimes 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: legal punishment for certain crimes | Statement: [Dementor’s Kiss, legalStatusInWizardingWorld, legal punishment for certain crimes]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: legalStatusInWizardingWorld
Context triple: [Dementor’s Kiss, legalStatusInWizardingWorld, legal punishment for certain crimes]
  • A. legalStatusUnderBritish
    Indicates the legal status or classification an entity holds under British law or the British legal system.
  • B. hasHighestLegalStatusWithinCountry
    Indicates that an entity holds the topmost legally recognized status or rank within a specific country, above all other comparable statuses.
  • C. legalStatusClarifiedBy
    Indicates that the legal status of something is defined, explained, or resolved by a specific document, decision, or authoritative act.
  • D. hasLegalStatus chosen
    Indicates that an entity possesses a particular legal classification, recognition, or standing under law.
  • E. legalStatusInMostCountries
    Indicates the typical legal classification or treatment of something across the majority of countries.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ed4706c81908a5e4a3023a9c22f completed April 20, 2026, 6:22 p.m.
PD Predicate disambiguation batch_69e55b14c9d8819095453d0504d9222f completed April 19, 2026, 10:45 p.m.
Created at: April 11, 2026, 11:38 p.m.