Triple

T19612459
Position Surface form Disambiguated ID Type / Status
Subject So Weird E470766 entity
Predicate characterPortrayed P1507 FINISHED
Object Fiona "Fi" Phillips 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: Fiona "Fi" Phillips | Statement: [So Weird, characterPortrayed, Fiona "Fi" Phillips]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fiona "Fi" Phillips
Context triple: [So Weird, characterPortrayed, Fiona "Fi" Phillips]
  • A. Fiona "Fi" Phillips chosen
    Fiona "Fi" Phillips is the teenage protagonist of the Disney Channel series "So Weird," known for investigating paranormal phenomena while touring with her rock-musician mother.
  • B. Fiona Phillips
    Fiona Phillips is a British television presenter and journalist best known for co-hosting ITV's breakfast show GMTV.
  • C. Fiona Rae
    Fiona Rae is a contemporary British painter known for her vibrant, abstract works that blend gestural brushwork with graphic, pop-inflected imagery and helped define the Young British Artists movement.
  • D. Fiona Black
    Fiona Black is a notable individual recognized for achievements that have brought distinction to the surname Black.
  • E. Fiona Lewis
    Fiona Lewis is a British actress and writer best known for her roles in 1970s horror and thriller films.
  • 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_69d8e510fa248190b7afb274a1d4cf73 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640cbeda08190addb1adf84af4993 completed April 20, 2026, 3:05 p.m.
Created at: April 10, 2026, 1:43 p.m.