Triple
T5687053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Islands of Adventure |
E125338
|
entity |
| Predicate | previousAttractionOnSite |
P35613
|
FINISHED |
| Object | Universal Studios Florida parking lot |
—
|
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: Universal Studios Florida parking lot | Statement: [Islands of Adventure, previousAttractionOnSite, Universal Studios Florida parking lot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousAttractionOnSite Context triple: [Islands of Adventure, previousAttractionOnSite, Universal Studios Florida parking lot]
-
A.
previousAttraction
chosen
Indicates that one entity was formerly an attraction or point of interest associated with another entity in the past.
-
B.
previousThemeParkArea
Indicates that one theme park area directly preceded another in time or sequence within the park’s development or layout.
-
C.
relatedAttraction
Indicates that one attraction is associated with or connected to another attraction in some relevant way.
-
D.
previousVenue
Indicates that one venue was used or occupied before another in a sequence of venues.
-
E.
visitorAttractionSince
Indicates that an entity has served as a visitor attraction starting from a specified point in time.
- 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_69c0082a884c8190a79001bae658941f |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0248751bc8190b12aaa42d1ef17e3 |
completed | March 22, 2026, 5:19 p.m. |
| PD | Predicate disambiguation | batch_69c021be59088190a81c880957f666ab |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:44 p.m.