Triple
T23196047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail second-generation DMUs |
E579870
|
entity |
| Predicate | includes class |
P131580
|
FINISHED |
| Object | British Rail Class 14x |
—
|
NE NERFINISHED |
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: British Rail Class 14x | Statement: [British Rail second-generation DMUs, includes class, British Rail Class 14x]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includes class Context triple: [British Rail second-generation DMUs, includes class, British Rail Class 14x]
-
A.
includesClasses
chosen
Indicates that one entity contains or encompasses one or more class-type entities as part of its definition or structure.
-
B.
usesClass
Indicates that one entity makes use of, depends on, or is implemented using a particular class in its structure or behavior.
-
C.
addsClass
Indicates that one entity introduces or appends a class (such as a classification, type, or code) to another entity.
-
D.
includesInfraclass
Indicates that one entity is classified as belonging to a specific infraclass within a taxonomic hierarchy.
-
E.
expandsClass
Indicates that one class broadens or extends the definition, scope, or functionality of another class.
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fdb279c81908dcc46f2786a86cd |
completed | April 29, 2026, 4:58 a.m. |
| PD | Predicate disambiguation | batch_69ef8a041c0081909afb670d17a5aaba |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:06 p.m.