Triple
T7040121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Liverpool Street to Ipswich |
E163487
|
entity |
| Predicate | stationCategoryAtTerminus |
P15150
|
FINISHED |
| Object | London terminus |
—
|
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: London terminus | Statement: [London Liverpool Street to Ipswich, stationCategoryAtTerminus, London terminus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stationCategoryAtTerminus Context triple: [London Liverpool Street to Ipswich, stationCategoryAtTerminus, London terminus]
-
A.
stationType
Indicates the specific category or classification of a station based on its function, services, or operational characteristics.
-
B.
railwayStationCategory
Indicates the classification or type category assigned to a railway station within a rail network or system.
-
C.
stationName
Indicates the name assigned to a particular station in the relationship.
-
D.
railLineTerminus
Indicates that a rail line ends or terminates at the specified location or station.
-
E.
terminusStation
chosen
Indicates that a station serves as the final endpoint or terminal stop for a given route or service.
- 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_69c6885e7c1c8190be32a8f79ab4e0cf |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e4a3c36c819080942c59f1830ae8 |
completed | March 27, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69c6e1bb602081908bfa6186a1f5a4b4 |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:36 p.m.