Triple
T23231164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lieutenant Thomas Glahn |
E581156
|
entity |
| Predicate | hasRelationshipWith |
P2830
|
FINISHED |
| Object | Edvarda |
—
|
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: Edvarda | Statement: [Lieutenant Thomas Glahn, hasRelationshipWith, Edvarda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Edvarda Context triple: [Lieutenant Thomas Glahn, hasRelationshipWith, Edvarda]
-
A.
Edvarda
chosen
Edvarda is a central fictional character in Knut Hamsun’s novel "Pan," known for her complex and tumultuous relationship with the protagonist.
-
B.
Henrike
Henrike is a feminine given name of German origin, serving as the female form of Heinrich.
-
C.
Ludvika
Ludvika is a small industrial town in central Sweden known for its engineering and manufacturing industries, particularly in the power and electrical sectors.
-
D.
Dagmar
Dagmar is a feminine given name of Germanic origin, historically associated with European nobility and still used in various countries today.
-
E.
Vilhelmi
Vilhelmi is a given name that serves as an alternative spelling of the name Vilhelm, itself a Scandinavian form of William.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f19231ef908190a791b4967916a66f |
completed | April 29, 2026, 5:08 a.m. |
Created at: April 17, 2026, 4:09 p.m.