Triple
T2615847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Book of the Duchess |
E58885
|
entity |
| Predicate | openingDevice |
P30005
|
FINISHED |
| Object | insomnia of the narrator |
—
|
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: insomnia of the narrator | Statement: [The Book of the Duchess, openingDevice, insomnia of the narrator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingDevice Context triple: [The Book of the Duchess, openingDevice, insomnia of the narrator]
-
A.
launchDevice
Indicates initiating the operation or deployment of a device, typically starting its active functioning or sending it into its intended trajectory or mode of use.
-
B.
openingFunction
Indicates that one entity serves as the initial or primary function, role, or operation that begins or initiates a process, sequence, or interaction involving another entity.
-
C.
openingMechanism
chosen
Indicates the method or mechanism by which an object or structure is opened or made accessible.
-
D.
canBeOpenedBy
Indicates that one entity has the ability or permission to open another entity.
-
E.
openingAnswer
Indicates that an entity provides an initial or first response in a dialogue, interaction, or sequence of answers.
- 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_69ab4ac444dc819099614e534dd6021f |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd89325308190985598373eb0d296 |
completed | March 7, 2026, 7:49 a.m. |
| PD | Predicate disambiguation | batch_69abd80cd7fc81909e9696db2919129f |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:50 p.m.