Triple

T21490572
Position Surface form Disambiguated ID Type / Status
Subject Jumper (film) E530224 entity
Predicate starring P1507 FINISHED
Object Jamie Bell 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: Jamie Bell | Statement: [Jumper (film), starring, Jamie Bell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jamie Bell
Context triple: [Jumper (film), starring, Jamie Bell]
  • A. Jamie Bell chosen
    Jamie Bell is an English actor best known for his breakthrough role in the film "Billy Elliot" and subsequent work in movies such as "King Kong," "Snowpiercer," and "Rocketman."
  • B. Jessica Haxon
    Jessica Haxon is a fictional character from the television series "Hung," which follows a struggling high school coach who turns to male escorting to make ends meet.
  • C. Georgie Henley
    Georgie Henley is an English actress best known for playing Lucy Pevensie in the film adaptations of C.S. Lewis's "The Chronicles of Narnia" series.
  • D. Katherine Hoult
    Katherine Hoult is known as the spouse of Richard Mather.
  • E. Aanisah Hinds
    Aanisah Hinds is the daughter of American R&B and soul singer Macy Gray.
  • 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_69e0c45bd15481909fba5910765cdda2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea3aee648190ba845f0c7d8110dd completed April 23, 2026, 9:45 a.m.
Created at: April 16, 2026, 6:22 p.m.