Triple
T1243905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derby railway station |
E26719
|
entity |
| Predicate | junctionFor |
P1018
|
FINISHED |
| Object | services between London and Sheffield |
—
|
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: services between London and Sheffield | Statement: [Derby railway station, junctionFor, services between London and Sheffield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: junctionFor Context triple: [Derby railway station, junctionFor, services between London and Sheffield]
-
A.
joins
Indicates that one entity becomes a member or part of another entity, typically by entering into an organization, group, or association.
-
B.
formedByUnionOf
Indicates that something is created or defined as the union or combination of multiple other things.
-
C.
hasJunctionWith
chosen
Indicates that one entity meets or intersects with another at a shared junction point.
-
D.
hasConjunctForms
Indicates that an entity is associated with one or more conjunct (combined or compound) forms of itself or related elements.
-
E.
inUnionFlagRepresents
Indicates that one entity is represented or symbolized by its inclusion on the union flag of 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_69a4948689d08190b3a4a3f388c02148 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf636e208190a4d56806db61916c |
completed | March 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69a4bb696a38819095845c84f0241287 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:47 p.m.