Triple

T21350317
Position Surface form Disambiguated ID Type / Status
Subject Tina Goldstein E526456 entity
Predicate organizationRole P12630 FINISHED
Object Auror for MACUSA 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: Auror for MACUSA | Statement: [Tina Goldstein, organizationRole, Auror for MACUSA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Auror for MACUSA
Context triple: [Tina Goldstein, organizationRole, Auror for MACUSA]
  • A. Auror chosen
    An Auror is a highly trained dark-wizard catcher and elite law-enforcement officer in the Harry Potter universe, working for the Ministry of Magic to combat dark magic and its practitioners.
  • B. Aurora Driver
    Aurora Driver is an autonomous driving system developed by Aurora Innovation to enable self-driving capabilities for commercial vehicles.
  • C. Club Aurora
    Club Aurora is a Bolivian professional football club based in the city of Cochabamba.
  • D. Auric
    Auric is the surname of Georges Auric, a prominent 20th-century French composer and member of the avant-garde group Les Six.
  • E. Aurora Sinistra
    Aurora Sinistra is the Astronomy professor at Hogwarts School of Witchcraft and Wizardry in the Harry Potter series.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b51cd5cc81909ac1187971e8a8ad completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8ad31087481909d41e9d28286f04d completed April 22, 2026, 11:12 a.m.
Created at: April 16, 2026, 5:03 p.m.