Triple
T22351185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mara Wilson |
E552531
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Anna 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: Anna Wilson | Statement: [Mara Wilson, relative, Anna Wilson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anna Wilson Context triple: [Mara Wilson, relative, Anna Wilson]
-
A.
Anna Wilson
chosen
Anna Wilson is known as the sister of former child actress and writer Mara Wilson.
-
B.
Laura Wilson
Laura Wilson is a British crime novelist known for her psychologically complex mysteries and contributions to contemporary detective fiction.
-
C.
Elizabeth Wilson
Elizabeth Wilson was the wife of American composer and playwright Meredith Willson, known for her association with the creator of the Broadway musical "The Music Man."
-
D.
Elizabeth Wilson
Elizabeth Wilson was a screenwriter known for her work on the 1964 Western film "Invitation to a Gunfighter."
-
E.
Elizabeth Wilson
Elizabeth Wilson was an American actress known for her versatile character roles on stage, film, and television, including performances in "The Graduate" and "9 to 5."
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1579be6d8819088fed70f54ff4e66 |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:44 p.m.