Triple
T18858893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victoria Tennant |
E461253
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Kirk Stievely |
—
|
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: Kirk Stievely | Statement: [Victoria Tennant, spouse, Kirk Stievely]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kirk Stievely Context triple: [Victoria Tennant, spouse, Kirk Stievely]
-
A.
Kirk Stievely
chosen
Kirk Stievely is a British actor best known as the former husband of actress Victoria Tennant.
-
B.
Kirk La Shelle
Kirk La Shelle was an American playwright and screenwriter active in the early 20th century, known for adapting popular literary works for the stage and screen.
-
C.
Kirk DeMicco
Kirk DeMicco is an American screenwriter and film director best known for his work on animated features such as "The Croods."
-
D.
Chris Stolte
Chris Stolte is a computer scientist and entrepreneur best known as a co-founder and former chief development officer of the data visualization company Tableau Software.
-
E.
Kirk Trutner
Kirk Trutner is an American actor best known for his supporting role in the 1997 disaster film "Dante's Peak."
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05eaee881909da704cf1374158c |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 10, 2026, 11:57 a.m.