Triple
T37981953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BC Rail (historical) |
E947574
|
entity |
| Predicate | operationsLeasedTo |
P59248
|
FINISHED |
| Object | Canadian National Railway |
E30762
|
NE 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: Canadian National Railway | Statement: [BC Rail (historical), operationsLeasedTo, Canadian National Railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operationsLeasedTo Context triple: [BC Rail (historical), operationsLeasedTo, Canadian National Railway]
-
A.
infrastructureLeasedTo
chosen
Indicates that infrastructure owned or controlled by one party is leased or rented out for use by another party under a contractual agreement.
-
B.
wasLeasedFor
Indicates that one entity was leased in exchange for a specified payment amount, purpose, or consideration.
-
C.
ownsOrLeases
Indicates that one entity has legal rights to use or control another entity either through ownership or through a lease agreement.
-
D.
hasLessee
Indicates that one entity is the lessee (the party renting or leasing) in a lease relationship with another entity.
-
E.
tenantFacilityFor
Indicates that a facility is designated for use or occupancy by a particular tenant.
- F. None of above.
Provenance (4 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_69f76ef8a1d08190a741bbbc5970e3b3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a0337c7389c8190b71d27b8eb8daf9a |
completed | May 12, 2026, 2:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41542df4348190a6c671950caf8328 |
completed | June 28, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_6a0335b7b1588190b02a0ce6a08704aa |
completed | May 12, 2026, 2:14 p.m. |
Created at: May 3, 2026, 4:20 p.m.