Triple
T8881521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LNER Class P2 |
E211420
|
entity |
| Predicate | originalDesignVariant |
P39487
|
FINISHED |
| Object | P2/1 design |
—
|
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: P2/1 design | Statement: [LNER Class P2, originalDesignVariant, P2/1 design]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalDesignVariant Context triple: [LNER Class P2, originalDesignVariant, P2/1 design]
-
A.
designVariant
chosen
Indicates that one entity is an alternative design or version derived from or related to another entity’s design.
-
B.
hasDesignOrigin
Indicates that one entity is the source, inspiration, or original model from which the design of another entity is derived.
-
C.
exportVariantOf
Indicates that one entity is an exported version or externally released form derived from another, original entity.
-
D.
primaryVariant
Indicates that one entity is the main or canonical version among multiple related variants of another entity.
-
E.
hasDesign
Indicates that one entity possesses, embodies, or is characterized by a particular design 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_69ca838f9e20819096ab1f236a70381a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6168e3d881908c58cf11cf5f9a0e |
completed | April 1, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2956788190a311c647b4da17a6 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:53 p.m.