Triple
T26752576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irn-Bru |
E674579
|
entity |
| Predicate | tasteComparison |
P104048
|
FINISHED |
| Object | often described as similar to bubblegum or cream soda but unique |
—
|
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: often described as similar to bubblegum or cream soda but unique | Statement: [Irn-Bru, tasteComparison, often described as similar to bubblegum or cream soda but unique]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tasteComparison Context triple: [Irn-Bru, tasteComparison, often described as similar to bubblegum or cream soda but unique]
-
A.
tasteComparedTo
chosen
Indicates a comparison of the taste or flavor of one entity relative to another.
-
B.
tasteInfluence
Indicates how one entity’s characteristics, actions, or presence affect or shape another entity’s preferences, likes, or aesthetic tastes.
-
C.
leafTaste
Indicates that one entity has a particular taste or flavor associated with its leaves.
-
D.
hasTasteIntensity
Indicates the degree or strength of taste associated with something.
-
E.
hasTastingProfile
Indicates that an entity possesses a specific flavor or sensory profile, typically describing its characteristic tastes and aromas.
- 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_69eecda6e9dc81908452fab3ba17ed9b |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f618cea64c819087537ce89b2fec9c |
completed | May 2, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:54 a.m.