Triple
T24727510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City Hall, Southwark |
E618192
|
entity |
| Predicate | panoramicViewFrom |
P29603
|
FINISHED |
| Object | top-floor public gallery |
—
|
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: top-floor public gallery | Statement: [City Hall, Southwark, panoramicViewFrom, top-floor public gallery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: panoramicViewFrom Context triple: [City Hall, Southwark, panoramicViewFrom, top-floor public gallery]
-
A.
viewpointFrom
Indicates a relationship where something is observed, depicted, or described from the perspective or location of a particular entity or point.
-
B.
hasPanoramicView
chosen
Indicates that something offers a wide, unobstructed view over a broad surrounding area.
-
C.
perspectiveOf
Indicates that something is expressed, depicted, or understood from the viewpoint or standpoint of a particular entity.
-
D.
viewOver
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
-
E.
hasScenicViewOf
Indicates that one entity offers a visually appealing or picturesque view of 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_69e2fab772608190b74163751047ff50 |
completed | April 18, 2026, 3:29 a.m. |
| NER | Named-entity recognition | batch_69f410fe3b848190ae296a29f742ee30 |
completed | May 1, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f40ee8ada8819089a7016b50308ff0 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 4 a.m.