Triple
T16843958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Left You Dead |
E409486
|
entity |
| Predicate | hasDetectiveFictionElement |
P106216
|
FINISHED |
| Object | police procedural |
—
|
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: police procedural | Statement: [Left You Dead, hasDetectiveFictionElement, police procedural]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDetectiveFictionElement Context triple: [Left You Dead, hasDetectiveFictionElement, police procedural]
-
A.
hasFictionalDetective
Indicates that one entity (typically a work or series) features or includes a fictional detective character as part of its content.
-
B.
fictionalDetective
Indicates that the subject is a detective character who exists only in fiction rather than in real life.
-
C.
hasFictionComponent
Indicates that something includes, contains, or is composed in part of a fictional element or work.
-
D.
hasFeatureInFiction
chosen
Indicates that a fictional work includes or portrays a particular feature, trait, or characteristic.
-
E.
hasClericalDetective
Indicates that an entity includes or is associated with a detective who is also a member of the clergy.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b3533a9481909730571e6f758cbe |
completed | April 18, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69e32b87b4248190aaddb05e88452356 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.