Triple
T17046251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emily Maitlis |
E413576
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mark Gwynne |
—
|
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: Mark Gwynne | Statement: [Emily Maitlis, spouse, Mark Gwynne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Gwynne Context triple: [Emily Maitlis, spouse, Mark Gwynne]
-
A.
Mark Gwynne
chosen
Mark Gwynne is a British investment manager best known as the husband of journalist and broadcaster Emily Maitlis.
-
B.
Andrew Gwynne
Andrew Gwynne is a British Labour Party politician who has served as the Member of Parliament for the Greater Manchester constituency of Denton and Reddish since 2005.
-
C.
Ed Guiney
Ed Guiney is an Irish film producer and co-founder of Element Pictures, known for collaborating on acclaimed films such as "The Favourite," "Room," and "Poor Things."
-
D.
Kevin Gilliam
Kevin Gilliam, better known by his stage name Battlecat, is an American hip hop producer and DJ recognized for his influential work in West Coast rap.
-
E.
Dwayne Gittens
Dwayne Gittens is a fictional character from the crime thriller film "In Too Deep," involved in the movie’s gritty underworld narrative.
- 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_69d886cd18288190b006abab23f811b7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3da9e3d8881909f197aba0e4c97e7 |
completed | April 18, 2026, 7:25 p.m. |
Created at: April 10, 2026, 5:33 a.m.