Triple
T25400940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crown Point TMD, Norwich |
E636414
|
entity |
| Predicate | maintainedClass |
P158826
|
FINISHED |
| Object | British Rail Class 90 |
—
|
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 90 | Statement: [Crown Point TMD, Norwich, maintainedClass, British Rail Class 90]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainedClass Context triple: [Crown Point TMD, Norwich, maintainedClass, British Rail Class 90]
-
A.
maintainedClass
chosen
Indicates that one entity is responsible for maintaining, updating, or managing the specified class.
-
B.
maintainedAs
Indicates that one entity is kept in a particular state, condition, or configuration by another entity through ongoing care, management, or support.
-
C.
maintainedFor
Indicates that something is kept in a particular state, condition, or operation for the benefit, use, or purpose of another entity.
-
D.
stillMaintained
Indicates that the subject continues to be actively maintained or supported over time.
-
E.
maintainedDuring
Indicates that a certain condition, state, or relationship continues to hold throughout the duration of a specified event or time interval.
- 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_69e75db263888190b77fff9e2827b9a2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f584fa51c481909a8f11b41f2b1d30 |
completed | May 2, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 1:50 p.m.