Triple
T16974089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo |
E411761
|
entity |
| Predicate | hasBusServicesTo |
P3791
|
FINISHED |
| Object | Southport |
E68739
|
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: Southport | Statement: [Waterloo, hasBusServicesTo, Southport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Southport Context triple: [Waterloo, hasBusServicesTo, Southport]
-
A.
Southport
chosen
Southport is a seaside town and popular tourist resort on the Irish Sea coast in North West England.
-
B.
Southport
Southport is a major coastal suburb and business hub of the City of Gold Coast in Queensland, Australia, known for its waterfront, shopping, and commercial precincts.
-
C.
Southport
Southport is a small city located within Marion County in the U.S. state of Indiana.
-
D.
Southport
Southport is an elevated Chicago 'L' train station in the Lakeview neighborhood, serving the CTA Brown Line.
-
E.
Workington
Workington is a coastal town and port on the west coast of England, historically known for its steel and coal industries and situated at the mouth of the River Derwent.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d0af06688190a77682aa297cd27e |
completed | April 18, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d4738fbc819099e8281ebc777091 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.