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.