Triple

T4885461
Position Surface form Disambiguated ID Type / Status
Subject Ghost Ranch E109428 entity
Predicate usedAsSubjectIn P41975 FINISHED
Object paintings by Georgia O’Keeffe LITERAL 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: paintings by Georgia O’Keeffe | Statement: [Ghost Ranch, usedAsSubjectIn, paintings by Georgia O’Keeffe]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usedAsSubjectIn
Context triple: [Ghost Ranch, usedAsSubjectIn, paintings by Georgia O’Keeffe]
  • A. isUsedAs
    Indicates that one entity serves a particular function, role, or purpose as another entity.
  • B. usedAsExampleIn chosen
    Indicates that one entity is cited or presented as an illustrative example within another entity, such as a text, discussion, or explanation.
  • C. hasSubjectPosition
    Indicates that an entity occupies or is assigned to a particular subject role or position within a structure, context, or organization.
  • D. hasSubjectPronouns
    Indicates that an entity is associated with one or more pronouns that function as its grammatical subject in sentences.
  • E. areUsedIn
    Indicates that certain entities serve as components, tools, or resources within a particular process, context, or application.
  • F. None of above.

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_69bd440f71348190b99938e59fb7f9a1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6de3718881908521968fa6e6b444 completed March 20, 2026, 3:55 p.m.
PD Predicate disambiguation batch_69bd6c2be5e881909f6ec9c3bcde49f3 completed March 20, 2026, 3:47 p.m.
Created at: March 20, 2026, 1:27 p.m.