Triple
T24952500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southbank |
E624376
|
entity |
| Predicate | riverFrontageType |
P92288
|
FINISHED |
| Object | riverside promenade |
—
|
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: riverside promenade | Statement: [Southbank, riverFrontageType, riverside promenade]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverFrontageType Context triple: [Southbank, riverFrontageType, riverside promenade]
-
A.
hasWaterfrontType
chosen
Indicates that an entity is associated with a specific type or category of waterfront (e.g., oceanfront, lakefront, riverfront).
-
B.
hasWaterfrontView
Indicates that a property or location offers a direct view of a body of water from its premises.
-
C.
isWaterfrontBuilding
Indicates that a building is located directly adjacent to a body of water, such as a river, lake, or ocean.
-
D.
streetFrontageOn
Indicates that a property or parcel directly borders or faces a particular street along at least one of its sides.
-
E.
coastalFrontageFor
Indicates that one entity has a boundary or frontage directly along the coast associated with another entity.
- 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_69e2ff22e4c48190a0444b5a044f14e8 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cf017a88190b4985b11159c907d |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 5:57 a.m.