Triple
T22031160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Wilson |
E544089
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Suzy Wilson |
—
|
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: Suzy Wilson | Statement: [Mike Wilson, spouse, Suzy Wilson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suzy Wilson Context triple: [Mike Wilson, spouse, Suzy Wilson]
-
A.
Suzy Wilson
chosen
Suzy Wilson is the mother of American former child actress and writer Mara Wilson.
-
B.
Maureen Wilson
Maureen Wilson is a former model and the first wife of Led Zeppelin frontman Robert Plant, known for her close association with the band during its early years.
-
C.
Susan Wilson
Susan Wilson is a fictional character played by actress Alexandra Shipp, likely featured in a film or television production.
-
D.
Cherilyn Wilson
Cherilyn Wilson is an American actress known for her roles in horror and thriller films, including the 2010 movie "Chain Letter."
-
E.
Dorothy Wilson
Dorothy Wilson was an American film actress of the 1930s known for her roles in Hollywood dramas and adventure films.
- 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_69e11e2f98c8819083e11eab90942a78 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127edd5b48190a9aeb2840105c181 |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:24 p.m.