Triple
T21603310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoffrey Grigson |
E533104
|
entity |
| Predicate | hasRelative |
P367
|
FINISHED |
| Object | Sophie Grigson |
—
|
NE NERFINISHED |
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: Sophie Grigson | Statement: [Geoffrey Grigson, hasRelative, Sophie Grigson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sophie Grigson Context triple: [Geoffrey Grigson, hasRelative, Sophie Grigson]
-
A.
Sophie Grigson
chosen
Sophie Grigson is a British cookery writer, television presenter, and food educator known for her accessible recipes and focus on seasonal, home-style cooking.
-
B.
Prue Leith
Prue Leith is a South African-born British restaurateur, chef, and food writer best known as a judge on popular television cooking and baking competitions.
-
C.
Nigella Lawson
Nigella Lawson is a British food writer and television cook known for her bestselling cookbooks and popular cooking shows.
-
D.
Joanne Harris
Joanne Harris is a British author best known for her novel "Chocolat," a magical realist tale that was adapted into an acclaimed film.
-
E.
Alice Webb
Alice Webb is a British media executive and producer known for her leadership roles in major broadcasting organizations and involvement in high-profile documentary projects.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46364608190a337dc8720dc2a35 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef17e31c80819090fdd63b5c103acb |
completed | April 27, 2026, 8:01 a.m. |
Created at: April 16, 2026, 6:33 p.m.