Triple
T8040049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bannerman Castle |
E187412
|
entity |
| Predicate | nearestCity |
P350
|
FINISHED |
| Object | Newburgh, New York |
E14893
|
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: Newburgh, New York | Statement: [Bannerman Castle, nearestCity, Newburgh, New York]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Newburgh, New York Context triple: [Bannerman Castle, nearestCity, Newburgh, New York]
-
A.
Newburgh, New York
chosen
Newburgh, New York is a historic city in the Hudson Valley known for its waterfront along the Hudson River and its significant role in early American history.
-
B.
Newburgh
Newburgh is a small rural village in Lancashire, England, known for its historic buildings and scenic countryside setting.
-
C.
Newburgh
Newburgh is a small historic town in eastern Scotland known for its scenic setting on the River Tay and its traditional Scottish character.
-
D.
Newark, New York
Newark, New York is a small village in Wayne County known as a local commercial center along the Erie Canal in the Finger Lakes region.
-
E.
Richmond, New York
Richmond, New York is a small rural town in Ontario County known for its Finger Lakes scenery and outdoor recreation opportunities.
- 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_69ca82b00cb48190b59a300f70e97bd7 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f1d62c48190bf4a6cd17517c5dc |
completed | March 31, 2026, 3:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd946a5e188190b2ef0a07a885ade7 |
completed | April 1, 2026, 9:55 p.m. |
Created at: March 30, 2026, 5:23 p.m.