Triple

T3195427
Position Surface form Disambiguated ID Type / Status
Subject Brooklyn Beckham E66923 entity
Predicate familyName P18 FINISHED
Object Beckham E224738 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: Beckham | Statement: [Brooklyn Beckham, familyName, Beckham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beckham
Context triple: [Brooklyn Beckham, familyName, Beckham]
  • A. Beckham chosen
    Beckham is the surname of Odell Beckham Jr., a prominent American football wide receiver known for his spectacular catches and NFL career.
  • B. David Beckham
    David Beckham is a former English footballer renowned worldwide for his precise crossing and free-kick ability, his success with club and country, and his status as a global sports icon.
  • C. Romeo Beckham
    Romeo Beckham is a British footballer and model, best known as the son of former England captain David Beckham and fashion designer Victoria Beckham.
  • D. Victoria Beckham
    Victoria Beckham is an English fashion designer, businesswoman, and former Spice Girls pop singer known as "Posh Spice."
  • E. Giggs
    Giggs is a British rapper and songwriter from London known for his deep voice and influential role in the UK rap and grime scenes.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7163c6c8190b26b05b66740264d completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28e69ff6081908189e2e756e3748b completed March 12, 2026, 9:59 a.m.
Created at: March 8, 2026, 3:07 p.m.