Triple
T8325056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harriet Martineau |
E194928
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Norwich |
E41722
|
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: Norwich | Statement: [Harriet Martineau, residence, Norwich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norwich Context triple: [Harriet Martineau, residence, Norwich]
-
A.
Norwich
Norwich is a rural township in Oxford County, Ontario, known for its agricultural community and small-town character.
-
B.
Norwich
chosen
Norwich is a historic cathedral city in Norfolk, England, known for its medieval architecture and role as a regional cultural and economic center.
-
C.
Lowestoft
Lowestoft is a coastal town in Suffolk, England, known as the easternmost settlement in the United Kingdom and a traditional fishing and seaside resort.
-
D.
King's Lynn
King's Lynn is a historic market and port town in Norfolk, England, known for its medieval architecture and long-standing role as a regional commercial center.
-
E.
Northampton
Northampton is a historic market town and the county town of Northamptonshire in the East Midlands of England.
- 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_69ca82e7a8a88190a32bb5cc0feb012d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7f7e4f8081908e0f876ad962c932 |
completed | March 31, 2026, 8:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc6804a0c819091a6f46ef6c5670d |
completed | April 2, 2026, 1:29 a.m. |
Created at: March 30, 2026, 5:56 p.m.