Triple
T31845649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shiplake railway station |
E812931
|
entity |
| Predicate | lineOtherDirection |
P116628
|
FINISHED |
| Object | Twyford railway station |
—
|
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: Twyford railway station | Statement: [Shiplake railway station, lineOtherDirection, Twyford railway station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lineOtherDirection Context triple: [Shiplake railway station, lineOtherDirection, Twyford railway station]
-
A.
lineDirectionTo
Indicates the directional relationship from one line to another, such as whether they point in the same, opposite, or a specific relative direction.
-
B.
lapDirection
Indicates the direction or orientation in which a lapping or overlapping action occurs between entities.
-
C.
branchLineDirection
Indicates the directional orientation or flow of a branch line relative to a main line or reference point.
-
D.
hasOppositeDirectionTo
chosen
Indicates that one entity’s direction is exactly reversed or opposed to the direction of another entity.
-
E.
lineDirectionSouth
Indicates that a line or path is oriented or directed toward the south.
- 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_69f348eb327881909b4584b925742f6e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b03577f88190a30e05f3aa0110c6 |
completed | May 3, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:50 p.m.