Triple
T15067588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westin Birmingham Hotel |
E379793
|
entity |
| Predicate | brandStandard |
P15065
|
FINISHED |
| Object | modern accommodations |
—
|
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: modern accommodations | Statement: [Westin Birmingham Hotel, brandStandard, modern accommodations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandStandard Context triple: [Westin Birmingham Hotel, brandStandard, modern accommodations]
-
A.
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.
-
B.
brandLevel
Indicates the hierarchical rank or tier of a brand within a defined brand structure or classification system.
-
C.
brandManaged
Indicates that one entity is responsible for overseeing, controlling, or administering the brand of another entity.
-
D.
formedBrand
Indicates that an entity created or established a particular brand as a distinct commercial or organizational identity.
-
E.
brandAttribute
chosen
Indicates that a specific attribute or characteristic is associated with, or describes, a particular brand.
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedeebc7e48190a86b4f0afe8844bb |
completed | April 15, 2026, 12:42 a.m. |
| PD | Predicate disambiguation | batch_69deb95a182081908fffc4402b02a394 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:02 a.m.