Triple
T1954949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brad Pitt |
E42243
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | Juliette Lewis |
E71030
|
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: Juliette Lewis | Statement: [Brad Pitt, partner, Juliette Lewis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Juliette Lewis Context triple: [Brad Pitt, partner, Juliette Lewis]
-
A.
Juliette Lewis
chosen
Juliette Lewis is an American actress and singer known for her intense, offbeat performances in films such as "Cape Fear," "Natural Born Killers," and numerous independent productions.
-
B.
Christina Ricci
Christina Ricci is an American actress known for her darkly quirky roles in films such as The Addams Family, Casper, and Sleepy Hollow.
-
C.
Anna Paquin
Anna Paquin is an Academy Award–winning Canadian-born New Zealand actress known for films such as "The Piano," the "X-Men" series, and the TV series "True Blood."
-
D.
Marissa Ribisi
Marissa Ribisi is an American actress known for her roles in films like "Dazed and Confused" and "Pleasantville."
-
E.
Lacey Chabert
Lacey Chabert is an American actress and voice actress best known for her roles in the film "Mean Girls," numerous Hallmark Channel movies, and early voice work in animated series.
- 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_69a8870eea088190a38781990812a9bc |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb353aa8c81909810347f9981a02f |
completed | March 7, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae1fd49e3c8190ac7b29b51b122505 |
completed | March 9, 2026, 1:18 a.m. |
Created at: March 4, 2026, 7:36 p.m.