Triple
T33415585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scream Extractor |
E855704
|
entity |
| Predicate | intendedUseInStory |
P80898
|
FINISHED |
| Object | increase scream production efficiency |
—
|
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: increase scream production efficiency | Statement: [Scream Extractor, intendedUseInStory, increase scream production efficiency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedUseInStory Context triple: [Scream Extractor, intendedUseInStory, increase scream production efficiency]
-
A.
designedPurposeInFiction
Indicates that something is intentionally created within a fictional context to serve a particular role, function, or narrative purpose.
-
B.
narrativePurpose
chosen
Indicates the role or function that something serves within the structure or progression of a narrative.
-
C.
useInNarrative
Indicates that something is employed as an element or device within a narrative or story.
-
D.
textUsedIn
Indicates that a particular piece of text is employed or referenced within another resource, context, or artifact.
-
E.
endedUseWith
Indicates that an entity has stopped or terminated its use or association with another entity.
- 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_69f3496f04a08190804e56ac5098b8e4 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: May 1, 2026, 1:36 a.m.