Triple
T33510993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scariest Places on Earth |
E858241
|
entity |
| Predicate | usesStorytellingDevice |
P23847
|
FINISHED |
| Object | reenactments |
—
|
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: reenactments | Statement: [Scariest Places on Earth, usesStorytellingDevice, reenactments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesStorytellingDevice Context triple: [Scariest Places on Earth, usesStorytellingDevice, reenactments]
-
A.
hasNarrativeDevice
chosen
Indicates that one entity employs, contains, or is characterized by a particular narrative device used in storytelling or discourse.
-
B.
storyDeviceType
Indicates the type or category of narrative device used within a story.
-
C.
usesTechnologyInStory
Indicates that an entity incorporates or employs a particular technology within the context of a narrative or story.
-
D.
tellsStoriesIn
Indicates that one entity narrates or recounts stories within or to the context of another entity (such as a place, group, or medium).
-
E.
openingNarrativeDevice
Indicates the narrative device or technique used to begin or introduce a story or discourse.
- 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_69f3497721848190978fbee5e0a526f8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd485f57dc8190820365396d041991 |
completed | May 8, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69fd47d35da081908bec8901018d186c |
completed | May 8, 2026, 2:17 a.m. |
Created at: May 1, 2026, 1:38 a.m.