Triple
T4699997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angel of the North |
E104244
|
entity |
| Predicate | wingAngle |
P21070
|
FINISHED |
| Object | 3.5 degrees forward |
—
|
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: 3.5 degrees forward | Statement: [Angel of the North, wingAngle, 3.5 degrees forward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wingAngle Context triple: [Angel of the North, wingAngle, 3.5 degrees forward]
-
A.
wing
Indicates that an entity has a wing or is equipped with wings as a physical feature or structural component.
-
B.
wingSweepAngles
chosen
Indicates the angular positions of an entity’s wings relative to a reference axis, typically describing how far the wings are swept forward or backward.
-
C.
wingConfiguration
Indicates how the wings of an aircraft or creature are arranged or structured relative to its body and to each other.
-
D.
dropAngle
Indicates the angle at which something is dropped or released relative to a reference direction or surface.
-
E.
wingFolding
Indicates that an entity folds or can fold its wings, typically transitioning them from an extended to a closed or resting position.
- 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_69bd43e9b88481908582103dcadff3d9 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd650ad0f88190844bfcb46b3071c2 |
completed | March 20, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69bd621ba7448190a53ab1e2897acf71 |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:17 p.m.