Triple
T14779039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Radcliffe |
E347341
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Radcliffe |
E1057783
|
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: Radcliffe | Statement: [Roger Radcliffe, familyName, Radcliffe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Radcliffe Context triple: [Roger Radcliffe, familyName, Radcliffe]
-
A.
Radcliffe
Radcliffe is a town in Greater Manchester, England, historically part of Lancashire and known for its industrial heritage along the River Irwell.
-
B.
Radcliffe
chosen
Radcliffe is a surname most prominently associated with Paula Radcliffe, the British long-distance runner and former women’s marathon world record holder.
-
C.
Heythrop
Heythrop is a small rural village in West Oxfordshire, England, known for its historic country estate and tranquil countryside setting.
-
D.
Magdalen
Magdalen is a feminine given name of biblical origin, most commonly associated with Mary Magdalene.
-
E.
Clare Hall
Clare Hall is a constituent college of the University of Cambridge, known for its strong focus on advanced study and research, particularly at the graduate and postdoctoral levels.
- 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_69d822e9b9e08190bedcc31a163fda82 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deca9c7cac8190ba900df95e42e318 |
completed | April 14, 2026, 11:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0d00d46c8190b6289a9b8511a8fb |
completed | May 8, 2026, 4:19 p.m. |
Created at: April 10, 2026, 1:31 a.m.