Triple
T33796558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheraton |
E866088
|
entity |
| Predicate | brandRefresh |
P179727
|
FINISHED |
| Object | global brand transformation announced in late 2010s |
—
|
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: global brand transformation announced in late 2010s | Statement: [Sheraton, brandRefresh, global brand transformation announced in late 2010s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandRefresh Context triple: [Sheraton, brandRefresh, global brand transformation announced in late 2010s]
-
A.
brandRevival
Indicates the process or action of restoring a declining or dormant brand to renewed strength, relevance, and market presence.
-
B.
brandingReplaced
Indicates that one branding has been superseded or substituted by another branding.
-
C.
brandRevivedBy
Indicates that a previously inactive, discontinued, or defunct brand has been brought back into use or reintroduced by a specific agent or entity.
-
D.
brand
Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
-
E.
brandNumber
Indicates the identifying number or code assigned to a particular brand within a system or dataset.
- F. None of above. chosen
Provenance (4 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_69f3498f99f481909cb271f4965a7594 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f727bde8f88190ad746ca515134ca1 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72739c30c81908642eef3feb3afcf |
completed | May 3, 2026, 10:45 a.m. |
| PDg | Predicate description generation | batch_69f727bd39b081908457590c3ba9b745 |
completed | May 3, 2026, 10:47 a.m. |
Created at: May 1, 2026, 1:46 a.m.