Triple
T3145710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liseberg |
E65758
|
entity |
| Predicate | hasRollerCoaster |
P23566
|
FINISHED |
| Object |
Helix
Helix is a multi-launch steel roller coaster at the Liseberg amusement park in Gothenburg, Sweden, known for its intense inversions and terrain-hugging layout.
|
E331612
|
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: Helix | Statement: [Liseberg, hasRollerCoaster, Helix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helix Context triple: [Liseberg, hasRollerCoaster, Helix]
-
A.
Spiral
"Spiral" is a notable work by filmmaker Mark Burg, best known as a producer in the horror and thriller genres.
-
B.
Spiral
Spiral is a distinctive modern architectural complex in Tokyo’s Aoyama district known for its spiral ramp design and role as a cultural and commercial hub.
-
C.
Helikon
Helikon is a mountain in Greek mythology, often associated with the Muses and poetic inspiration.
-
D.
Corkscrew
Corkscrew is a steel roller coaster at Michigan’s Adventure known for its signature double-inversion corkscrew elements.
-
E.
Weave
Weave is Google's Internet of Things (IoT) communication platform designed to let smart devices easily discover, connect, and work together across different ecosystems.
- 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: Helix Triple: [Liseberg, hasRollerCoaster, Helix]
Generated description
Helix is a multi-launch steel roller coaster at the Liseberg amusement park in Gothenburg, Sweden, known for its intense inversions and terrain-hugging layout.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Helix Target entity description: Helix is a multi-launch steel roller coaster at the Liseberg amusement park in Gothenburg, Sweden, known for its intense inversions and terrain-hugging layout.
-
A.
Spiral
"Spiral" is a notable work by filmmaker Mark Burg, best known as a producer in the horror and thriller genres.
-
B.
Spiral
Spiral is a distinctive modern architectural complex in Tokyo’s Aoyama district known for its spiral ramp design and role as a cultural and commercial hub.
-
C.
Helikon
Helikon is a mountain in Greek mythology, often associated with the Muses and poetic inspiration.
-
D.
Corkscrew
Corkscrew is a steel roller coaster at Michigan’s Adventure known for its signature double-inversion corkscrew elements.
-
E.
Weave
Weave is Google's Internet of Things (IoT) communication platform designed to let smart devices easily discover, connect, and work together across different ecosystems.
- 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_69ad8582f564819088c27e1f96153938 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada59797788190a8d71262888c5df0 |
completed | March 8, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b224f18e80819083be53c556d56947 |
completed | March 12, 2026, 2:29 a.m. |
| NEDg | Description generation | batch_69b2271961048190906b6fa25e4b560c |
completed | March 12, 2026, 2:38 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b227becba08190b5e4b3dae277ce51 |
completed | March 12, 2026, 2:41 a.m. |
Created at: March 8, 2026, 3:05 p.m.