Triple
T17599704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skyline Rotorua |
E428660
|
entity |
| Predicate | activityCategory |
P8834
|
FINISHED |
| Object | adventure tourism |
—
|
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: adventure tourism | Statement: [Skyline Rotorua, activityCategory, adventure tourism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activityCategory Context triple: [Skyline Rotorua, activityCategory, adventure tourism]
-
A.
activityType
chosen
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
B.
typicalActivity
Indicates that an entity is commonly or characteristically engaged in a particular activity.
-
C.
activityCorrelatesWith
Indicates that the level or occurrence of one activity is statistically associated with the level or occurrence of another activity, without implying direct causation.
-
D.
activityDomain
Indicates the general field, sector, or area of activity within which an entity operates or performs its main actions.
-
E.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4812d48190bf8e899fa8f7fbe4 |
completed | April 19, 2026, 5:46 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fff0348190b899a32da537eaca |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:51 a.m.