Triple
T32669950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marianne von Willemer |
E835264
|
entity |
| Predicate | hasLiteraryPersona |
P162887
|
FINISHED |
| Object | Suleika |
—
|
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: Suleika | Statement: [Marianne von Willemer, hasLiteraryPersona, Suleika]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLiteraryPersona Context triple: [Marianne von Willemer, hasLiteraryPersona, Suleika]
-
A.
hasPoetCharacter
Indicates that an entity includes or features a character whose role or identity is that of a poet.
-
B.
literaryRole
Indicates the specific narrative or functional role an entity holds within a literary work or text.
-
C.
hasLiteraryConnection
Indicates a relationship in which one entity is connected to another through a literary link, such as authorship, reference, influence, adaptation, or shared appearance in written works.
-
D.
literaryCharacterModeledAs
chosen
Indicates that one literary character is created or portrayed based on the traits, life, or persona of another real or fictional individual.
-
E.
literaryAuthor
Indicates that one entity is the author or writer of a literary work represented by the other entity.
- 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_69f349303ccc8190a70d0f6e8a21d3fb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
Created at: May 1, 2026, 1:09 a.m.