Triple
T20877245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter DeLuise |
E514050
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Anne Marie Loder |
—
|
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: Anne Marie Loder | Statement: [Peter DeLuise, spouse, Anne Marie Loder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anne Marie Loder Context triple: [Peter DeLuise, spouse, Anne Marie Loder]
-
A.
Anne Marie Loder
chosen
Anne Marie Loder is an actress known for her role in the fantasy-comedy film "Life-Size" and various other television and film appearances.
-
B.
Daphne Clunes
Daphne Clunes is the daughter of English actor Martin Clunes.
-
C.
Sarah Wainthrope
Sarah Wainthrope is an individual known primarily through her association as a friend of John Tate.
-
D.
Lindsay Fox
Lindsay Fox is an Australian businessman best known as the founder of the logistics company Linfox and as one of the country’s most prominent transport magnates.
-
E.
Madeleine Mantock
Madeleine Mantock is a British actress known for her roles in genre television series, including prominent parts in action and supernatural dramas.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c6767ec0819080721e2e75bd0d66 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:45 p.m.