Triple

T16215561
Position Surface form Disambiguated ID Type / Status
Subject Eugenia "Skeeter" Phelan E393583 entity
Predicate writesBookWithinStory P24104 FINISHED
Object a book about Black maids in Jackson 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: a book about Black maids in Jackson | Statement: [Eugenia "Skeeter" Phelan, writesBookWithinStory, a book about Black maids in Jackson]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: writesBookWithinStory
Context triple: [Eugenia "Skeeter" Phelan, writesBookWithinStory, a book about Black maids in Jackson]
  • A. bookWriter chosen
    Indicates that a person is the author who wrote the specified book.
  • B. storyEngine
    Indicates that one entity functions as a narrative-generating or plot-controlling mechanism for another entity or set of events.
  • C. storyBy
    Indicates that one entity is the creator or author of the story associated with another entity.
  • D. wroteIn
    Indicates that an entity authored or composed something using a particular language, medium, or writing system.
  • E. worksForInNovel
    Indicates that one entity is employed by or serves another entity within the fictional context of a specific novel.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227f4685c8190aa1e9304e4a62d13 completed April 17, 2026, 12:30 p.m.
PD Predicate disambiguation batch_69e219e94a448190b73a4e6aa374eb4a completed April 17, 2026, 11:30 a.m.
Created at: April 10, 2026, 5:03 a.m.