Triple
T23678312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail electric multiple units |
E584945
|
entity |
| Predicate | ownerDuringBRPeriod |
P20308
|
FINISHED |
| Object | British Railways Board |
—
|
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: British Railways Board | Statement: [British Rail electric multiple units, ownerDuringBRPeriod, British Railways Board]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ownerDuringBRPeriod Context triple: [British Rail electric multiple units, ownerDuringBRPeriod, British Railways Board]
-
A.
ownedDuring
chosen
Indicates that one entity possessed or held ownership of another entity for some or all of a specified time interval.
-
B.
regionDuringBR
Indicates that a region exists or is valid specifically during a defined base or reference time interval (BR).
-
C.
ownerLater
Indicates that one entity becomes the owner of another entity at a later point in time, after some prior state or ownership.
-
D.
ownerDuringEra
Indicates that one entity is the owner of another entity specifically during a defined historical period or era.
-
E.
holderBecame
Indicates that an entity that previously held something transitioned into a new role, state, or identity as a result of that holding.
- 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_69e24901f7c08190909fd727632e823d |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b4f5a7b48190b93d27416003e173 |
completed | April 29, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:51 p.m.