Triple
T38627599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Riccarton Junction railway station |
E937357
|
entity |
| Predicate | closedCompletelyOn |
P56128
|
FINISHED |
| Object | 1967 |
—
|
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: 1967 | Statement: [Riccarton Junction railway station, closedCompletelyOn, 1967]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closedCompletelyOn Context triple: [Riccarton Junction railway station, closedCompletelyOn, 1967]
-
A.
closedWith
Indicates that one entity is finalized, completed, or terminated through the involvement or use of another entity.
-
B.
closureCompleted
chosen
Indicates that a previously initiated closure process or shutdown has been fully and successfully completed.
-
C.
closedBy
Indicates that one entity performs the action of closing, finishing, or terminating another entity (such as a task, issue, or process).
-
D.
closedAgainst
Indicates that an entity has been closed or shut in opposition to, or as a barrier against, another entity.
-
E.
closedBefore
Indicates that one entity was closed at an earlier time than 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_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd485f57dc8190820365396d041991 |
completed | May 8, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69fd47d35da081908bec8901018d186c |
completed | May 8, 2026, 2:17 a.m. |
Created at: May 3, 2026, 4:32 p.m.