Triple
T19761059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phantom’s Revenge |
E474628
|
entity |
| Predicate | previousAttractionType |
P137219
|
FINISHED |
| Object | Steel Phantom looping coaster |
—
|
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: Steel Phantom looping coaster | Statement: [Phantom’s Revenge, previousAttractionType, Steel Phantom looping coaster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousAttractionType Context triple: [Phantom’s Revenge, previousAttractionType, Steel Phantom looping coaster]
-
A.
previousAttraction
Indicates that one entity was formerly an attraction or point of interest associated with another entity in the past.
-
B.
partOfAttractionType
Indicates that one attraction type is a component or subset of a broader, more general attraction type.
-
C.
attractionType
Indicates the specific kind or category of attraction that characterizes the relationship between entities.
-
D.
hasAttractionType
Indicates that one entity is associated with a specific kind or category of attraction (e.g., tourist, cultural, natural).
-
E.
previousThemeParkArea
Indicates that one theme park area directly preceded another in time or sequence within the park’s development or layout.
- F. None of above. chosen
Provenance (4 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6531f38b48190b1663870a8da5a59 |
completed | April 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69e5305016e08190b9561a96baecb0b8 |
completed | April 19, 2026, 7:43 p.m. |
| PDg | Predicate description generation | batch_69e532bbedf081908d801600e2af94a7 |
completed | April 19, 2026, 7:53 p.m. |
Created at: April 10, 2026, 1:48 p.m.