Triple
T18413038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Törnrosens bok |
E441811
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Amorina |
—
|
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: Amorina | Statement: [Törnrosens bok, hasPart, Amorina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amorina Context triple: [Törnrosens bok, hasPart, Amorina]
-
A.
Amorina
chosen
Amorina is a 19th-century Swedish novel by Carl Jonas Love Almqvist, known for its romantic and psychological depth within early modern Swedish literature.
-
B.
Ylenia
Ylenia is an Italian woman best known as the missing daughter of singer and TV personality Al Bano Carrisi and actress Romina Power.
-
C.
Maridati
Maridati is a small settlement located within the municipality of Sitia on the island of Crete, Greece.
-
D.
Carmina
Carmina is a collection of Latin poems by the early medieval scholar-bishop Paulinus of Aquileia, reflecting his theological, liturgical, and pastoral concerns.
-
E.
Carmina
Carmina is a collection of Latin poems by the late Roman author Sidonius Apollinaris, reflecting the literary and cultural life of fifth-century Gaul.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a259c1c819094e710bb4a7ace75 |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 10:47 a.m.