Triple

T15623918
Position Surface form Disambiguated ID Type / Status
Subject Kayla Silverfox E375631 entity
Predicate sibling P363 FINISHED
Object Emma Silverfox E1167693 NE 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: Emma Silverfox | Statement: [Kayla Silverfox, sibling, Emma Silverfox]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emma Silverfox
Context triple: [Kayla Silverfox, sibling, Emma Silverfox]
  • A. Emma Silverfox chosen
    Emma Silverfox is a person known primarily for being a relative of Kayla Silverfox.
  • B. Kayla Silverfox
    Kayla Silverfox is a mutant with empathic and mind-influencing abilities who serves as Wolverine’s love interest and a key figure in his past in the film X-Men Origins: Wolverine.
  • C. Sarah Silver
    Sarah Silver is known as the ex-wife of American dancer and chef Dean Sheremet.
  • D. Sylver Gregory
    Sylver Gregory is an actor known for appearing in the British television series "The Royal Family."
  • E. Heather Goldenhersh
    Heather Goldenhersh is an American actress best known for her work on stage and screen, including her acclaimed performance in the film and play "Doubt."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e9cfd94819091459aa17a002eaf completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff678a9fac81908030726054ff5a99 completed May 9, 2026, 4:57 p.m.
Created at: April 10, 2026, 4:14 a.m.