Triple
T5018352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Underwood |
E112788
|
entity |
| Predicate | usesStoryDevice |
P23847
|
FINISHED |
| Object | breaking the fourth wall |
—
|
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: breaking the fourth wall | Statement: [Frank Underwood, usesStoryDevice, breaking the fourth wall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesStoryDevice Context triple: [Frank Underwood, usesStoryDevice, breaking the fourth wall]
-
A.
hasNarrativeDevice
chosen
Indicates that one entity employs, contains, or is characterized by a particular narrative device used in storytelling or discourse.
-
B.
usesDevice
Indicates that one entity operates, employs, or relies on a particular device to perform an action or achieve a purpose.
-
C.
usesNarrativeStyle
Indicates that one entity employs or adopts a particular narrative style in presenting or structuring content or information.
-
D.
storyBy
Indicates that one entity is the creator or author of the story associated with another entity.
-
E.
storyElement
Indicates that one entity functions as a narrative component or part within the structure of another entity’s story.
- 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_69bd4435c2f48190be593158cbfcf8a3 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73415e088190802f9bb283262386 |
completed | March 20, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69bd714ecfe08190b5830cfc1c74fa17 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:35 p.m.