Triple
T20996004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Walker |
E517150
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Mara 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: Mara Wilson | Statement: [Susan Walker, portrayedBy, Mara Wilson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mara Wilson Context triple: [Susan Walker, portrayedBy, Mara Wilson]
-
A.
Mara Wilson
chosen
Mara Wilson is an American former child actress and writer best known for her roles in films like "Matilda," "Mrs. Doubtfire," and "Miracle on 34th Street."
-
B.
Tali David
Tali David is a minor character in the TV series "NCIS," known as the younger sister of main character Ziva David.
-
C.
Maya Ford
Maya Ford is an American musician best known as the bassist for the all-female rock band The Donnas.
-
D.
Rachel Zane
Rachel Zane is a central character in the legal drama series "Suits," known as a talented paralegal who aspires to become a lawyer and develops a key romantic relationship with Mike Ross.
-
E.
Saela Davis
Saela Davis is a film editor and director known for her work on projects such as the documentary "Ballet 422."
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc1fd5d48190a56981cee95ebd69 |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:50 p.m.