Triple
T19162424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Harrow station |
E469088
|
entity |
| Predicate | replacedByNewStationOn |
P20874
|
FINISHED |
| Object | 1935-07-05 |
—
|
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: 1935-07-05 | Statement: [South Harrow station, replacedByNewStationOn, 1935-07-05]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedByNewStationOn Context triple: [South Harrow station, replacedByNewStationOn, 1935-07-05]
-
A.
replacedStation
chosen
Indicates that one station has taken the place of another station, typically succeeding it in function, service, or location.
-
B.
originalStationClosed
Indicates that the original station associated with an entity has been closed or is no longer in operation.
-
C.
hasFormerStation
Indicates that an entity previously had a particular station (e.g., a stop, depot, or facility) that is no longer in active use or part of its current infrastructure.
-
D.
adjacentStationFormerly
Indicates that two stations were directly adjacent to each other in the past, but are no longer adjacent in the current network configuration.
-
E.
replacedFacilityAt
Indicates that one facility has been substituted for or taken the place of another at a specific location or point in time.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eebe03ac8190bbe0b34ebf0d90c6 |
completed | April 20, 2026, 9:15 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b83d6881908e6271c620f74100 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.