Triple
T27512162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hamstead railway station |
E694446
|
entity |
| Predicate | serviceDestination |
P50377
|
FINISHED |
| Object | Birmingham New Street |
—
|
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: Birmingham New Street | Statement: [Hamstead railway station, serviceDestination, Birmingham New Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceDestination Context triple: [Hamstead railway station, serviceDestination, Birmingham New Street]
-
A.
sampleDestination
Indicates that something serves as, or is designated to be, the target location or endpoint for a sample.
-
B.
servedDestination
chosen
Indicates that a service or action is directed toward, or provided to, a particular destination.
-
C.
reportDestination
Indicates the target location, system, or entity to which a report is sent or delivered.
-
D.
serviceDirection
Indicates the direction or orientation in which a service is provided or operates relative to involved entities.
-
E.
servesDestinationType
Indicates that an entity provides service to, or is intended for use with, a specific type or category of destination.
- 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_69ef53842afc8190ba6bd4e4999bda67 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 27, 2026, 1:16 p.m.