Triple
T5372407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Settle–Carlisle line |
E108880
|
entity |
| Predicate | hasGradient |
P63610
|
FINISHED |
| Object | steep gradients over the Pennines |
—
|
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: steep gradients over the Pennines | Statement: [Settle–Carlisle line, hasGradient, steep gradients over the Pennines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGradient Context triple: [Settle–Carlisle line, hasGradient, steep gradients over the Pennines]
-
A.
usesGradientInformation
Indicates that an entity performs its operation by leveraging gradient (derivative) information, typically to guide optimization or learning steps.
-
B.
hasDerivative
Indicates that one entity is derived, obtained, or produced from another through some transformation, process, or modification.
-
C.
hasDerivatives
Indicates that one entity is derived, obtained, or developed from another entity.
-
D.
averageGradient
Indicates the mean rate of change (slope) of a quantity over a specified interval or region.
-
E.
maximumGradient
Indicates the greatest rate of change or steepest slope that occurs within a given function, surface, or dataset.
- F. None of above. chosen
Provenance (4 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_69bd440c77948190aad2a5f39b7b80f5 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd88801b188190b9ac35ed89167fa3 |
completed | March 20, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69bd846172788190969f24bc7503c05e |
completed | March 20, 2026, 5:31 p.m. |
| PDg | Predicate description generation | batch_69bd887f5b0081909456992d1a071928 |
completed | March 20, 2026, 5:48 p.m. |
Created at: March 20, 2026, 2:02 p.m.