Triple
T16956869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Marshal |
E411327
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Berkshire |
E83859
|
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: Berkshire | Statement: [John Marshal, residence, Berkshire]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berkshire Context triple: [John Marshal, residence, Berkshire]
-
A.
Berkshire
chosen
Berkshire is a historic county in South East England known for its royal connections, including Windsor Castle, and its mix of affluent towns and rural landscapes.
-
B.
Berkshire County
Berkshire County is a rural, culturally rich county in western Massachusetts known for its scenic Berkshire Mountains, outdoor recreation, and vibrant arts institutions.
-
C.
Hampshire
Hampshire is a county on England’s south coast known for its historic cities, naval and military heritage, and mix of rural countryside and coastal areas.
-
D.
Hampshire
Hampshire is a rural locality in the north-west of Tasmania, Australia, known for its forestry and agricultural activities.
-
E.
Hampshire County
Hampshire County is a county in the Eastern Panhandle of West Virginia known for its rural Appalachian landscape, small towns, and historic transportation routes.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d01c7b408190b5a2b6c62b050b76 |
completed | April 18, 2026, 6:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d4666f14819095fc3bcf5e459b61 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.