Triple
T15800587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The New York Trilogy |
E383086
|
entity |
| Predicate | deconstructs |
P120119
|
FINISHED |
| Object | conventions of crime fiction |
—
|
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: conventions of crime fiction | Statement: [The New York Trilogy, deconstructs, conventions of crime fiction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deconstructs Context triple: [The New York Trilogy, deconstructs, conventions of crime fiction]
-
A.
reconstructs
Indicates performing an action to rebuild, restore, or reassemble something from its parts, damage, or prior state.
-
B.
deconsecrated
Indicates that something previously dedicated as sacred or religious has had that sacred status formally removed or revoked.
-
C.
decomposesIn
Indicates that one entity breaks down or separates into another entity or set of entities as its components or products.
-
D.
deposes
Indicates the action by which one party forcibly removes another from a position of power or authority.
-
E.
dismembered
Indicates that one entity has cut or torn another entity’s body into separate parts, typically removing limbs or sections.
- 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_69d86da16e188190b89af699f1ed0bfe |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b4e135b08190b736e77bac5e2bff |
completed | April 16, 2026, 10:07 a.m. |
| PD | Predicate disambiguation | batch_69e0053b847c8190945726c3ddac21cc |
completed | April 15, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69e00e48d49c819081afccb02f9cf18b |
completed | April 15, 2026, 10:16 p.m. |
Created at: April 10, 2026, 4:48 a.m.