Triple
T10076449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norman Foster |
E213772
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Wendy Cheesman |
E213772
|
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: Wendy Cheesman | Statement: [Norman Foster, spouse, Wendy Cheesman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wendy Cheesman Context triple: [Norman Foster, spouse, Wendy Cheesman]
-
A.
Wendy Cheesman
chosen
Wendy Cheesman was a British architect and the first wife and early professional collaborator of renowned architect Norman Foster.
-
B.
Wendy Ferguson
Wendy Ferguson is known as a child of the renowned Canadian jazz trumpeter and bandleader Maynard Ferguson.
-
C.
Wendy Hughes
Wendy Hughes was an acclaimed Australian actress known for her versatile performances in film, television, and theatre from the 1970s onward.
-
D.
Julie Ferguson
Julie Ferguson is the wife of the late American actor and comedian Charles Grodin.
-
E.
Wendy Molyneux
Wendy Molyneux is an American television writer, producer, and showrunner best known for her work on animated comedies such as Bob’s Burgers and The Great North.
- 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_69ca839add308190b57d53b4ec21f2d0 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd0190d808190847ea0fa401ef06c |
completed | April 2, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2cbc0388c8190bc10d462068c9e38 |
completed | April 5, 2026, 8:53 p.m. |
Created at: March 30, 2026, 8:59 p.m.