Triple
T32061382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cadbury "Gorilla" commercial |
E818756
|
entity |
| Predicate | taglineUsed |
P95166
|
FINISHED |
| Object | A Glass and a Half Full of Joy |
—
|
NE NERFINISHED |
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: A Glass and a Half Full of Joy | Statement: [Cadbury "Gorilla" commercial, taglineUsed, A Glass and a Half Full of Joy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: taglineUsed Context triple: [Cadbury "Gorilla" commercial, taglineUsed, A Glass and a Half Full of Joy]
-
A.
taglineMatch
Indicates that two entities share the same tagline or that a tagline corresponds to a given entity.
-
B.
usedAsMarketingTaglineFor
chosen
Indicates that something is employed as a promotional slogan or catchphrase to market a particular product, service, brand, or entity.
-
C.
hasTagline
Indicates that an entity is associated with a specific slogan or tagline that represents or promotes it.
-
D.
taglineFormat
Indicates the specific structure or style in which a tagline is expressed or presented.
-
E.
sloganUsedBy
Indicates that a particular slogan is employed or adopted by a specific entity (such as a person, organization, or brand) in its communication or branding.
- 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_69f348fdacec8190b9f74375ca3b2094 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b4f638908190957f64096c07535f |
completed | May 3, 2026, 2:37 a.m. |
| PD | Predicate disambiguation | batch_69f6b154b3dc819087115f5f63f7b00f |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:22 a.m.