Triple
T14697234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "Fallen cold and dead" |
E345194
|
entity |
| Predicate | repetitionRole |
P115394
|
FINISHED |
| Object | structural refrain |
—
|
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: structural refrain | Statement: ["Fallen cold and dead", repetitionRole, structural refrain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repetitionRole Context triple: ["Fallen cold and dead", repetitionRole, structural refrain]
-
A.
repetitionOf
Indicates that one entity is a repeated occurrence or instance of another entity, preserving the same content or pattern.
-
B.
usesRepetition
Indicates that one entity employs repeated elements, actions, or patterns as a deliberate feature or technique in relation to another entity or context.
-
C.
causesRepetitionOf
Indicates that one entity brings about or is responsible for the recurrence or repeated occurrence of another entity or event.
-
D.
repetitionPattern
Indicates a recurring structure or sequence in which an action, event, or element is repeated over time or across instances.
-
E.
roleInRepertoire
Indicates that an entity serves a specific role or function within a larger repertoire, collection, or set of items.
- F. None of above. chosen
Provenance (4 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_69d822e4a8c08190a155df736bb7bc13 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb58855e081908b38f9515db5677f |
completed | April 14, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69de657c57ec8190ae0b9bb79a514566 |
completed | April 14, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69de716d3aac8190aaa6dc1f099b86e8 |
completed | April 14, 2026, 4:55 p.m. |
Created at: April 10, 2026, 1:28 a.m.