Triple
T17039656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilltop "I’d Like to Buy the World a Coke" |
E413410
|
entity |
| Predicate | taglineConcept |
P83195
|
FINISHED |
| Object | Coke as a unifying force |
—
|
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: Coke as a unifying force | Statement: [Hilltop "I’d Like to Buy the World a Coke", taglineConcept, Coke as a unifying force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: taglineConcept Context triple: [Hilltop "I’d Like to Buy the World a Coke", taglineConcept, Coke as a unifying force]
-
A.
taglineForm
Indicates that one entity serves as the tagline or slogan associated with another entity.
-
B.
taglineMatch
Indicates that two entities share the same tagline or that a tagline corresponds to a given entity.
-
C.
hasTagline
Indicates that an entity is associated with a specific slogan or tagline that represents or promotes it.
-
D.
sloganConcept
chosen
Indicates that a particular concept, idea, or theme is expressed or represented by a given slogan.
-
E.
taglineWordplay
Indicates that a tagline employs wordplay, such as puns, double meanings, or playful language, as a key part of its expression.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d8f5844c819097eade4a2b42ab91 |
completed | April 18, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.