Triple
T19819457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strand (Northern line) station |
E476146
|
entity |
| Predicate | surfaceBuildingStatus |
P38811
|
FINISHED |
| Object | surviving former station building |
—
|
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: surviving former station building | Statement: [Strand (Northern line) station, surfaceBuildingStatus, surviving former station building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceBuildingStatus Context triple: [Strand (Northern line) station, surfaceBuildingStatus, surviving former station building]
-
A.
hasBuildingStatus
chosen
Indicates the current condition, classification, or operational state assigned to a building.
-
B.
surfaceStatus
Indicates the condition or state of a surface, such as whether it is intact, damaged, altered, or otherwise characterized.
-
C.
roofStatus
Indicates the current condition or state of a roof, such as whether it is intact, damaged, under repair, or replaced.
-
D.
hasSurfaceBuilding
Indicates that one entity possesses or is associated with a building located on its surface.
-
E.
facesBuilding
Indicates that one building is oriented toward and directly faces another building.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e654fe0ff8819084bad251b76eff77 |
completed | April 20, 2026, 4:31 p.m. |
| PD | Predicate disambiguation | batch_69e5305bda388190a23b7191768107b1 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:50 p.m.