Triple

T20059253
Position Surface form Disambiguated ID Type / Status
Subject Cross E499424 entity
Predicate hasNotableBearer P458 FINISHED
Object John Cross 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: John Cross | Statement: [Cross, hasNotableBearer, John Cross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Cross
Context triple: [Cross, hasNotableBearer, John Cross]
  • A. John Cross chosen
    John Cross is a former Australian rugby league footballer best known for his time as a forward with the Illawarra Steelers in the NSWRL/ARL.
  • B. Jack Barron
    Jack Barron is the hard-edged, media-savvy talk show host protagonist of Norman Spinrad’s science fiction novel "Bug Jack Barron."
  • C. William Cage
    William Cage is the protagonist of the science fiction film "Edge of Tomorrow," a military public relations officer who becomes caught in a time loop while fighting an alien invasion.
  • D. Daniel Osbourne
    Daniel Osbourne is a fictional character from the television series "Buffy the Vampire Slayer," known as the quiet, guitar-playing werewolf and love interest of Willow Rosenberg.
  • E. Michael Creed
    Michael Creed is an Irish politician who has served as a Teachta Dála (TD) and held ministerial roles, notably as Minister for Agriculture, Food and the Marine.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66373e0e08190a6d8a10084eecc4d completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:38 p.m.