Triple
T20163859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PortAventura Park |
E491779
|
entity |
| Predicate | hasRollerCoaster |
P23566
|
FINISHED |
| Object |
Stampida
Stampida is a high-speed wooden roller coaster at Spain’s PortAventura Park known for its dueling tracks and intense, racing-style layout.
|
E1414272
|
NE FINISHED |
How this triple was built (4 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: Stampida | Statement: [PortAventura Park, hasRollerCoaster, Stampida]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stampida Context triple: [PortAventura Park, hasRollerCoaster, Stampida]
-
A.
Stößen
Stößen is a small town in the German state of Saxony-Anhalt that forms part of the broader Leipzig metropolitan area.
-
B.
Stempel
Stempel is a surname most notably associated with Robert R. Stempel, the former chairman and CEO of General Motors.
-
C.
Hasten
Hasten is a district of the German city of Remscheid, known for its historic buildings and traditional Bergisches architecture.
-
D.
Stiattesi
Stiattesi is an Italian surname, notably borne by Prudenzia Stiattesi, a historical figure from Italy.
-
E.
Estrapade
Estrapade was a champion American Thoroughbred racehorse best known for her success on turf in the mid-1980s, including a victory in the Arlington Million.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Stampida Triple: [PortAventura Park, hasRollerCoaster, Stampida]
Generated description
Stampida is a high-speed wooden roller coaster at Spain’s PortAventura Park known for its dueling tracks and intense, racing-style layout.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Stampida Target entity description: Stampida is a high-speed wooden roller coaster at Spain’s PortAventura Park known for its dueling tracks and intense, racing-style layout.
-
A.
Stößen
Stößen is a small town in the German state of Saxony-Anhalt that forms part of the broader Leipzig metropolitan area.
-
B.
Stempel
Stempel is a surname most notably associated with Robert R. Stempel, the former chairman and CEO of General Motors.
-
C.
Hasten
Hasten is a district of the German city of Remscheid, known for its historic buildings and traditional Bergisches architecture.
-
D.
Stiattesi
Stiattesi is an Italian surname, notably borne by Prudenzia Stiattesi, a historical figure from Italy.
-
E.
Estrapade
Estrapade was a champion American Thoroughbred racehorse best known for her success on turf in the mid-1980s, including a victory in the Arlington Million.
- F. None of above. chosen
Provenance (5 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66841b7d88190af3606f762d87b24 |
completed | April 20, 2026, 5:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08347d2330819088d865390a86d34c |
completed | May 16, 2026, 9:10 a.m. |
| NEDg | Description generation | batch_6a083555576c8190ba5df77ef48aa975 |
completed | May 16, 2026, 9:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08360def9c8190b8a2d48814ee13c8 |
completed | May 16, 2026, 9:17 a.m. |
Created at: April 11, 2026, 11:35 p.m.