Triple
T10017801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bart Simpson |
E199538
|
entity |
| Predicate | aunt |
P3525
|
FINISHED |
| Object | Selma Bouvier |
E396369
|
NE FINISHED |
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: Selma Bouvier | Statement: [Bart Simpson, aunt, Selma Bouvier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Selma Bouvier Context triple: [Bart Simpson, aunt, Selma Bouvier]
-
A.
Selma Bouvier
chosen
Selma Bouvier is a chain-smoking, raspy-voiced DMV clerk and Marge Simpson’s cynical sister on the animated television series "The Simpsons."
-
B.
Lise Bouvier
Lise Bouvier is the young French woman who becomes the romantic focus of the story in the classic musical film "An American in Paris."
-
C.
Laura Chase
Laura Chase is a central, enigmatic figure in Margaret Atwood’s novel "The Blind Assassin," whose life and mysterious death profoundly shape the story’s layered narrative.
-
D.
Rose Loomis
Rose Loomis is the seductive and scheming wife portrayed by Marilyn Monroe in the 1953 film noir "Niagara."
-
E.
Michelle Caroline Bouvier
Michelle Caroline Bouvier was a member of the prominent Bouvier family, known primarily as a relative of socialite and First Lady Jacqueline Kennedy Onassis.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca8315a1a08190ab310f25620f362b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd4de1588190a89ed575cff0b8c9 |
completed | April 2, 2026, 1:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26aa319508190b85b5a5f78603b6a |
completed | April 5, 2026, 1:58 p.m. |
Created at: March 30, 2026, 8:53 p.m.