Triple
T25518634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portman Street |
E639578
|
entity |
| Predicate | hasShoppingAccess |
P37662
|
FINISHED |
| Object | Oxford Street shopping district |
—
|
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: Oxford Street shopping district | Statement: [Portman Street, hasShoppingAccess, Oxford Street shopping district]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShoppingAccess Context triple: [Portman Street, hasShoppingAccess, Oxford Street shopping district]
-
A.
hasShop
Indicates that one entity owns, operates, or is associated with a shop or retail establishment.
-
B.
hasShoppingMall
Indicates that one entity possesses, contains, or includes a shopping mall within its area or domain.
-
C.
hasOnlineShop
Indicates that an entity operates or is associated with a shop that sells goods or services via the internet.
-
D.
isShoppingDestination
Indicates that a place serves as a primary location where people go to shop for goods or services.
-
E.
hasShopsOn
chosen
Indicates that one entity (typically a street, area, or building) contains or is lined with shops located on or along it.
- 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_69e75dbe32e48190a62d749a0ff2a96a |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8346c1481908272a96740bf51bc |
completed | May 2, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 2:58 p.m.