Triple
T15818342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disney storytelling themes |
E383535
|
entity |
| Predicate | supportsBrandPromise |
P87956
|
FINISHED |
| Object | “where dreams come true” |
—
|
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: “where dreams come true” | Statement: [Disney storytelling themes, supportsBrandPromise, “where dreams come true”]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsBrandPromise Context triple: [Disney storytelling themes, supportsBrandPromise, “where dreams come true”]
-
A.
brandPromise
chosen
Indicates the commitment or assurance a brand makes about the value, experience, or benefits it will consistently deliver to its audience.
-
B.
supportsBrand
Indicates that one entity endorses, promotes, or is compatible with a particular brand.
-
C.
hasBrandReputation
Indicates that an entity possesses a certain level or type of perceived quality, trustworthiness, or public image associated with its brand.
-
D.
supportsProduct
Indicates that one entity provides assistance, compatibility, or necessary resources for the operation, use, or maintenance of a specified product.
-
E.
supportsContentBrands
Indicates that one entity provides functionality, compatibility, or infrastructure necessary for the operation or distribution of specific content brands.
- 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_69d86da2858c819090cc8481e7207b6e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0c4a552008190863343c9d41ebf3f |
completed | April 16, 2026, 11:14 a.m. |
| PD | Predicate disambiguation | batch_69e0053b847c8190945726c3ddac21cc |
completed | April 15, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:49 a.m.