Triple
T34107804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evangeline Williamson |
E874754
|
entity |
| Predicate | creatorOfCharacterWork |
P40162
|
FINISHED |
| Object | Agnes Nixon |
—
|
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: Agnes Nixon | Statement: [Evangeline Williamson, creatorOfCharacterWork, Agnes Nixon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: creatorOfCharacterWork Context triple: [Evangeline Williamson, creatorOfCharacterWork, Agnes Nixon]
-
A.
creatorOfCharacter
chosen
Indicates that one entity is the originator or author who created or conceived the other entity as a character.
-
B.
authorWorkCreator
Indicates that an entity is the creator (author) responsible for producing a particular work.
-
C.
publisherOfWorksFeaturingCharacter
Indicates that one entity is the publisher responsible for releasing works in which a given character appears.
-
D.
creatorOfMainCharacter
Indicates that one entity is the creator or originator of the main character entity in a work or narrative.
-
E.
creatorOfAdaptationCharacterIn
Indicates that a person is the creator of a character that appears in a particular adaptation of a work.
- 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_69f349a80d4481908527317d43f5c579 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff3e1762d8819089a60e402e682817 |
completed | May 9, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69ff3d8c6f308190a0646b1432752eb8 |
completed | May 9, 2026, 1:58 p.m. |
Created at: May 1, 2026, 1:53 a.m.