Triple
T22266403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DfT category E station |
E550361
|
entity |
| Predicate | hasHigherCategory |
P4476
|
FINISHED |
| Object | DfT category A station |
—
|
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: DfT category A station | Statement: [DfT category E station, hasHigherCategory, DfT category A station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHigherCategory Context triple: [DfT category E station, hasHigherCategory, DfT category A station]
-
A.
hasCategoryLevel
Indicates that something is associated with a specific hierarchical category or tier within a classification system.
-
B.
hasHigherClass
chosen
Indicates that one entity belongs to a higher rank, level, or category in a hierarchy than another entity.
-
C.
higherCategoryComparedTo
Indicates that one entity belongs to a broader or more general category relative to another entity in a comparison.
-
D.
hasCategoryWithin
Indicates that one category is contained within or is a subcategory of another category.
-
E.
highestCategory
Indicates that the related entity is the topmost or most specific category to which another entity is ultimately classified or assigned.
- 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_69e11e43d8208190aff4f9cf7f2c2a8a |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141bc458c81909837373d749b915d |
completed | April 28, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69e72ff0363081909f794d19c8a64837 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:39 p.m.