Triple

T21474518
Position Surface form Disambiguated ID Type / Status
Subject Frank Crow E529821 entity
Predicate hasSurname P18 FINISHED
Object Crow 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: Crow | Statement: [Frank Crow, hasSurname, Crow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crow
Context triple: [Frank Crow, hasSurname, Crow]
  • A. Crow
    The Crow are a Native American tribe of the Great Plains, historically known as skilled horsemen and buffalo hunters centered in what is now Montana.
  • B. Crow chosen
    Crow is a common English surname shared by various notable individuals, including the American singer-songwriter Sheryl Crow.
  • C. Crow
    Crow is a character named Crow Tyrannosaurus, likely depicted as a distinctive or humorous figure associated with that unusual full name.
  • D. Crow
    "Crow" is a dark, experimental poetry collection by Ted Hughes that follows the mythic figure of Crow through violent, surreal explorations of creation, suffering, and the human condition.
  • E. Crow
    Crow is a highly intelligent, black-plumaged bird of the genus Corvus, known for its problem-solving abilities, complex social behavior, and prominent role in mythologies and folklore worldwide.
  • 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_69e0c459acb481909bb6ee452a0045c7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea1650788190bd55ebdbf1dfc46f completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:19 p.m.