Triple
T22920311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fjord-Rafting |
E568840
|
entity |
| Predicate | immersiveElements |
P103559
|
FINISHED |
| Object | sound effects of rushing water |
—
|
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: sound effects of rushing water | Statement: [Fjord-Rafting, immersiveElements, sound effects of rushing water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: immersiveElements Context triple: [Fjord-Rafting, immersiveElements, sound effects of rushing water]
-
A.
immersive
chosen
Indicates that an experience or environment fully surrounds and engages an entity’s senses or attention, creating a strong feeling of being present within it.
-
B.
interactiveElement
Indicates that one entity functions as an interface component designed to receive and respond to user actions initiated by another entity.
-
C.
immersesVisitorsIn
Indicates that one entity deeply involves or surrounds visitors in an experience, environment, or atmosphere created by another entity.
-
D.
intendedViewerExperience
Indicates the type or quality of experience that a piece of content is designed or expected to provide to its viewers.
-
E.
hasVirtualExperience
Indicates that one entity possesses or has participated in a virtual or digitally simulated experience related to 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180d40f98819096210c097b47d43b |
completed | April 29, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69ef3b7c5fc081909ac50c5c8569cc19 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:42 p.m.