Triple
T18509610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Spiller |
E452301
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Trophy Wife |
—
|
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: Trophy Wife | Statement: [Michael Spiller, notableWork, Trophy Wife]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trophy Wife Context triple: [Michael Spiller, notableWork, Trophy Wife]
-
A.
Trophy Wife
chosen
Trophy Wife is an American television sitcom that follows a former party girl adjusting to life as the third wife in a complicated blended family.
-
B.
Meet the Wife
Meet the Wife is a British television sitcom best known for starring Thora Hird as a domineering, sharp-tongued housewife.
-
C.
The Ex-Wife
The Ex-Wife is a British psychological thriller television series in which Celine Buckens stars as a woman whose seemingly perfect life unravels amid obsession, jealousy, and marital secrets.
-
D.
Run for Your Wife
Run for Your Wife is a popular British stage farce by Ray Cooney about a London taxi driver juggling two wives in different parts of the city.
-
E.
Bad Husband
"Bad Husband" is a song by Eminem, featuring X Ambassadors, that reflects on his troubled marriage and personal failings.
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53344c6b081908e780ed5c815a766 |
completed | April 19, 2026, 7:55 p.m. |
Created at: April 10, 2026, 11:36 a.m.