Triple
T21568975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark 1 TPO coaches |
E532234
|
entity |
| Predicate | operatedOnServiceType |
P5884
|
FINISHED |
| Object | overnight mail trains |
—
|
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: overnight mail trains | Statement: [Mark 1 TPO coaches, operatedOnServiceType, overnight mail trains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatedOnServiceType Context triple: [Mark 1 TPO coaches, operatedOnServiceType, overnight mail trains]
-
A.
operatedOn
Indicates that one entity has performed a surgical or procedural operation on another entity.
-
B.
operatedWith
Indicates that an entity performed an action, function, or process using a specified tool, method, or instrument.
-
C.
operatesService
chosen
Indicates that an agent runs, manages, or provides a particular service.
-
D.
operatedOnSystem
Indicates that an entity has performed operations or actions upon a particular system, affecting its state or behavior.
-
E.
operatedFor
Indicates that one entity performed operations or provided services on behalf of, or in support of, another entity for a certain period or purpose.
- 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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9cad95c8190ab165ced6f242302 |
completed | April 27, 2026, 4:44 a.m. |
| PD | Predicate disambiguation | batch_69e6320c8c2c81908bf031447d66a052 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:30 p.m.