Triple
T13865948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Café au Lait (Coffee and Cigarettes segment) |
E333326
|
entity |
| Predicate | framingDevice |
P60228
|
FINISHED |
| Object | characters chatting over coffee |
—
|
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: characters chatting over coffee | Statement: [Café au Lait (Coffee and Cigarettes segment), framingDevice, characters chatting over coffee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: framingDevice Context triple: [Café au Lait (Coffee and Cigarettes segment), framingDevice, characters chatting over coffee]
-
A.
hasFramingDevice
chosen
Indicates that one entity serves as a narrative or structural framing device that contextualizes, introduces, or encloses the main content of another entity.
-
B.
frameDevice
Indicates that one entity serves as a structural or supporting frame for another device or object.
-
C.
framed
Indicates that one entity has been falsely presented or set up to appear responsible or guilty for an action or situation, typically to mislead others.
-
D.
framedBy
Indicates that one entity serves as a surrounding boundary or enclosing structure that visually or conceptually frames another entity.
-
E.
resolutionDevice
Indicates a device or instrument that is used to resolve, determine, or measure the outcome or value associated with another entity or process.
- 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de23a101488190bd790b28033d38b9 |
completed | April 14, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_69de05972f3881909977b4c843984f88 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:14 p.m.