Triple

T20578636
Position Surface form Disambiguated ID Type / Status
Subject The Crusaders E505292 entity
Predicate notableWork P4 FINISHED
Object Way Back Home 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: Way Back Home | Statement: [The Crusaders, notableWork, Way Back Home]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Way Back Home
Context triple: [The Crusaders, notableWork, Way Back Home]
  • A. Way Back Home chosen
    "Way Back Home" is a popular jazz and big band tune closely associated with bandleader and singer Bob Crosby.
  • B. The Way Back Home
    The Way Back Home is a drama film featuring actor Maxim Knight in its cast.
  • C. Sing You Home
    Sing You Home is a contemporary novel by Jodi Picoult that explores themes of infertility, same-sex relationships, and legal battles over reproductive rights.
  • D. Come Home
    "Come Home" is a song by American rapper and singer Anderson .Paak from his album "Ventura."
  • E. Come Home
    "Come Home" is a song by indie rock musician Mac DeMarco from his critically acclaimed 2017 album "This Old Dog."
  • 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_69e0b4b721588190993ac7b0a9be2736 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a90cc22c8190969e3a21ae92f1c9 completed April 20, 2026, 10:30 p.m.
Created at: April 16, 2026, 11:39 a.m.