Triple
T8657863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Severn Sound |
E205467
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Midland |
E546992
|
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: Midland | Statement: [Severn Sound, borderedBy, Midland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Midland Context triple: [Severn Sound, borderedBy, Midland]
-
A.
Midland
Midland is a city in the Permian Basin region of West Texas known for its pivotal role in the oil and gas industry.
-
B.
Midland
Midland was a short-lived Formula One constructor that competed in the mid-2000s after taking over the Jordan Grand Prix team.
-
C.
Midland
chosen
Midland is a small town in central Ontario, Canada, known as a gateway to Georgian Bay and the 30,000 Islands region.
-
D.
Livingston
Livingston is a small Montana city known as a historic railroad town and gateway to Yellowstone National Park, with a vibrant arts scene and scenic mountain surroundings.
-
E.
Livingston
Livingston is a large post-war new town in West Lothian, Scotland, known as a major residential and commercial centre within the Edinburgh commuter belt.
- 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_69ca8350897c819086cde7596fbe5fe7 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc486d576081908ad28749c7971432 |
completed | March 31, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ceccec941881908263cd3205f10ccd |
completed | April 2, 2026, 8:09 p.m. |
Created at: March 30, 2026, 6:30 p.m.