Triple
T20772283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail Mark 3 coaching stock |
E511264
|
entity |
| Predicate | stillInService |
P7151
|
FINISHED |
| Object | yes (on some UK routes, 2020s) |
—
|
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: yes (on some UK routes, 2020s) | Statement: [British Rail Mark 3 coaching stock, stillInService, yes (on some UK routes, 2020s)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stillInService Context triple: [British Rail Mark 3 coaching stock, stillInService, yes (on some UK routes, 2020s)]
-
A.
inService
chosen
Indicates that an entity is currently active, operational, or available for use in its intended role or function.
-
B.
continuedInServiceOn
Indicates that an entity remained active, operational, or in use beyond a specified point in time or event.
-
C.
inServiceFrom
Indicates the time or event from which an entity (such as a service, system, or asset) begins being operationally active or officially in use.
-
D.
stillMaintained
Indicates that the subject continues to be actively maintained or supported over time.
-
E.
isServed
Indicates that one entity provides or delivers a service, product, or assistance to 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_69e0b4ca01148190ac018e57e0cab46f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2681ff88190bfe5938c2db6b2c4 |
completed | April 21, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:37 p.m.