Triple
T34694285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LMS Armstrong Whitworth |
E890982
|
entity |
| Predicate | builtType |
P179630
|
FINISHED |
| Object | LMS Stanier Class 5 4-6-0 |
—
|
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: LMS Stanier Class 5 4-6-0 | Statement: [LMS Armstrong Whitworth, builtType, LMS Stanier Class 5 4-6-0]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtType Context triple: [LMS Armstrong Whitworth, builtType, LMS Stanier Class 5 4-6-0]
-
A.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
B.
builtInfrastructureType
Indicates the specific kind or category of built infrastructure associated with or characterized by the subject.
-
C.
buildingType
Indicates the specific category or function that characterizes what kind of building something is.
-
D.
structureBuiltFor
Indicates that one entity was constructed specifically to serve, house, or support the function, use, or needs of another entity.
-
E.
builtUpBy
Indicates that something has been constructed, developed, or formed through the actions or contributions of a specified agent or process.
- 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_69f349db7ab8819086808e833f472871 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f72355ca348190b25b3479bccca922 |
completed | May 3, 2026, 10:28 a.m. |
| PD | Predicate disambiguation | batch_69f72157af108190880317a62e634bb0 |
completed | May 3, 2026, 10:20 a.m. |
| PDg | Predicate description generation | batch_69f7221bc57c819085c1464a45e61b2f |
completed | May 3, 2026, 10:23 a.m. |
Created at: May 1, 2026, 2:05 a.m.