Triple
T33774970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nevermore Academy |
E865489
|
entity |
| Predicate | employsInSeries |
P93486
|
FINISHED |
| Object | Marilyn Thornhill |
—
|
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: Marilyn Thornhill | Statement: [Nevermore Academy, employsInSeries, Marilyn Thornhill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employsInSeries Context triple: [Nevermore Academy, employsInSeries, Marilyn Thornhill]
-
A.
developerOfWorkAppearingIn
Indicates that one entity is the creator or developer of a work in which another entity appears or is featured.
-
B.
starOccupationInSeries
Indicates that an individual has a specific occupation or role as a starring character within a particular series.
-
C.
employerInPlot
chosen
Indicates that one entity serves as the employer of another within the context of a specific plot or storyline.
-
D.
worksInSeriesWith
Indicates that one entity collaborates or participates together with another entity within the same series or serialized work.
-
E.
spouseOccupationInSeries
Indicates that a character’s spouse has a particular occupation within the context of a series.
- 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_69f3498df6f88190bf9647ea4e4a956e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 1, 2026, 1:45 a.m.