Triple

T23267532
Position Surface form Disambiguated ID Type / Status
Subject Lois Wilson E588192 entity
Predicate notableWork P4 FINISHED
Object The Road to Yesterday 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: The Road to Yesterday | Statement: [Lois Wilson, notableWork, The Road to Yesterday]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Road to Yesterday
Context triple: [Lois Wilson, notableWork, The Road to Yesterday]
  • A. The Road to Yesterday chosen
    The Road to Yesterday is a 1925 American silent fantasy drama film directed by Cecil B. DeMille.
  • B. The Road to Here
    The Road to Here is a 2005 country music album by Little Big Town that helped establish the group’s signature harmonies and brought them mainstream recognition.
  • C. The Last Road
    The Last Road is an Iranian film best known for featuring acclaimed actor Ezzatolah Entezami in a prominent role.
  • D. The Roadside
    The Roadside is a 2021 EP by Billy Idol that marked his return with a reflective, melodic rock sound after several years without new releases.
  • E. The Road Between
    The Road Between is a work (likely a song or track) associated with the musical release "To Whom It May Concern."
  • 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_69e25d148adc819088efbf42672604e9 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19570fcc0819091df22140828155b completed April 29, 2026, 5:21 a.m.
Created at: April 17, 2026, 4:38 p.m.