Triple

T21117430
Position Surface form Disambiguated ID Type / Status
Subject Evanna Lynch E520334 entity
Predicate givenName P17 FINISHED
Object Evanna 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: Evanna | Statement: [Evanna Lynch, givenName, Evanna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evanna
Context triple: [Evanna Lynch, givenName, Evanna]
  • A. Evanna chosen
    Evanna is an Irish actress and activist best known for playing Luna Lovegood in the Harry Potter film series.
  • B. Arianne Phillips
    Arianne Phillips is an acclaimed American costume designer known for her work in film, theater, and music, including collaborations with directors like Madonna and Quentin Tarantino.
  • C. Ava Seave
    Ava Seave is a media industry consultant and author known for her critical analysis of major media companies and their business strategies.
  • D. Alexa Havins
    Alexa Havins is an American actress best known for her work in television, including a starring role in the science fiction series "Torchwood."
  • E. Ariana Richards
    Ariana Richards is an American actress and painter best known for playing Lex Murphy in the film "Jurassic Park."
  • 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_69e0b50a623881909c0bbaf4f2c055e7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e721078ac48190980441b6ada0e2b4 completed April 21, 2026, 7:02 a.m.
Created at: April 16, 2026, 2:55 p.m.