Triple

T10090016
Position Surface form Disambiguated ID Type / Status
Subject Earl Felton E215317 entity
Predicate workedOn P3 FINISHED
Object Crashout E840921 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: Crashout | Statement: [Earl Felton, workedOn, Crashout]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crashout
Context triple: [Earl Felton, workedOn, Crashout]
  • A. Crashout chosen
    Crashout is a 1955 American film noir crime drama about a group of escaped convicts on a violent quest for hidden loot.
  • B. Crashmo
    Crashmo is a physics-based puzzle video game for the Nintendo 3DS that challenges players to manipulate and rearrange falling blocks to solve increasingly complex spatial puzzles.
  • C. Crash
    Crash is a controversial 1973 novel by J. G. Ballard that explores the eroticization of car crashes and the dark intersections of technology, violence, and desire.
  • D. Crash
    Crash is a 1986 synth-pop album by British band The Human League, best known for featuring the hit single "Human" and marking a more polished, R&B-influenced sound for the group.
  • E. Crash
    Crash is a 2004 ensemble drama film exploring racial and social tensions in Los Angeles through intersecting storylines.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd05960008190baecb8e4c9f2461f completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cbe40d088190838819eac97c61e4 completed April 5, 2026, 8:53 p.m.
Created at: March 30, 2026, 9:01 p.m.