Triple
T5079337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flying Coaster |
E114475
|
entity |
| Predicate | hasThemingPotential |
P20616
|
FINISHED |
| Object | superhero themes |
—
|
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: superhero themes | Statement: [Flying Coaster, hasThemingPotential, superhero themes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasThemingPotential Context triple: [Flying Coaster, hasThemingPotential, superhero themes]
-
A.
supportsThemeOf
Indicates that one entity reinforces, aligns with, or contributes to the central theme expressed by another entity.
-
B.
hasThemeConnection
chosen
Indicates a relationship where one entity is linked to another through a shared or related theme, topic, or conceptual focus.
-
C.
hasMarketingTheme
Indicates that an entity is associated with or characterized by a particular marketing theme or campaign concept.
-
D.
hasCentralTheme
Indicates that one entity serves as the primary or dominant theme or subject matter of another entity.
-
E.
themeFor
Indicates that something serves as the central subject, topic, or focus for another thing (such as an event, work, or activity).
- 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_69bd443dbf908190a9401e9c2dc7bd7d |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74f75cf0819088be9e076eaf3168 |
completed | March 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69bd7157fe608190b4515d56fdd0a616 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:39 p.m.