Triple
T31490163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berghof sanatorium |
E803384
|
entity |
| Predicate | staffCharacter |
P93957
|
FINISHED |
| Object | Hofrat Behrens |
—
|
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: Hofrat Behrens | Statement: [Berghof sanatorium, staffCharacter, Hofrat Behrens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: staffCharacter Context triple: [Berghof sanatorium, staffCharacter, Hofrat Behrens]
-
A.
storyCharacterizedAs
Indicates that a story is described, portrayed, or defined as having a particular quality, style, or attribute.
-
B.
featuresCharacterRole
Indicates that a work includes a character appearing in a specific narrative or functional role.
-
C.
featuresCharacterWith
chosen
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
-
D.
metCharacter
Indicates that one entity has encountered or been introduced to another entity at least once.
-
E.
studentCharacter
Indicates that one entity has the role or qualities of a student in relation to another entity, typically within an educational or learning context.
- 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_69f348ca04508190ba9379b5329dfd75 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a1e4ca4881908146cb7b170209d6 |
completed | May 3, 2026, 1:16 a.m. |
| PD | Predicate disambiguation | batch_69f69fe82e5c81909da9db0a2f3bba6d |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:37 p.m.