Triple
T21926947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Wreck of the Deutschland |
E541465
|
entity |
| Predicate | centralHumanFigures |
P61746
|
FINISHED |
| Object | five exiled German nuns |
—
|
LITERAL FINISHED |
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: five exiled German nuns | Statement: [The Wreck of the Deutschland, centralHumanFigures, five exiled German nuns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralHumanFigures Context triple: [The Wreck of the Deutschland, centralHumanFigures, five exiled German nuns]
-
A.
publicFigure
Indicates that an entity is widely recognized by the public and holds a prominent or influential role in society, such as in politics, entertainment, or media.
-
B.
typicalFigure
Indicates that one entity serves as a standard or representative example (a typical instance) of the other entity.
-
C.
favoriteFigure
Indicates that one entity is the preferred or most liked figure (such as a person, character, or symbol) of another entity.
-
D.
containsHumanFigures
chosen
Indicates that the subject includes one or more human figures within its content or composition.
-
E.
featuresFigureOf
Indicates that one entity includes or presents another entity as a figure, illustration, or visual element.
- 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_69e0c47d74488190a15119108794a307 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f123fb6af08190b3562f547d4d2895 |
completed | April 28, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:46 p.m.