Triple
T21445734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nigel Cole |
E529069
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Kate Isitt |
—
|
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: Kate Isitt | Statement: [Nigel Cole, spouse, Kate Isitt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kate Isitt Context triple: [Nigel Cole, spouse, Kate Isitt]
-
A.
Kate Isitt
chosen
Kate Isitt is a British actress best known for her role as Sally Harper in the BBC sitcom "Coupling."
-
B.
Kate Kniveton
Kate Kniveton is a British Conservative Party politician serving as the Member of Parliament for the Burton constituency.
-
C.
Kate Wetherall
Kate Wetherall is a brave, resourceful, and acrobatic young girl who is one of the central child protagonists in Trenton Lee Stewart’s fantasy adventure series *The Books of Beginning*.
-
D.
Kate Sissons
Kate Sissons is an actress known for her role in the British online thriller series "Girl Number 9."
-
E.
Amy Gravitt
Amy Gravitt is a television executive and producer known for her leadership roles at HBO, overseeing and guiding numerous acclaimed comedy series.
- 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b707ecd88190b3576b8923840870 |
completed | April 22, 2026, 11:54 a.m. |
Created at: April 16, 2026, 6:05 p.m.