Triple
T9937603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gia |
E193995
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Mercedes Ruehl |
E397934
|
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: Mercedes Ruehl | Statement: [Gia, stars, Mercedes Ruehl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mercedes Ruehl Context triple: [Gia, stars, Mercedes Ruehl]
-
A.
Mercedes Ruehl
chosen
Mercedes Ruehl is an American actress acclaimed for her powerful stage and screen performances, including an Academy Award-winning role in the film "The Fisher King."
-
B.
Kimberly Elise
Kimberly Elise is an American actress known for her powerful performances in films such as "Set It Off," "Beloved," and "Diary of a Mad Black Woman."
-
C.
Anne McDonnell
Anne McDonnell was an American socialite best known as the first wife of industrialist Henry Ford II.
-
D.
Patricia Wettig
Patricia Wettig is an American actress best known for her Emmy-winning role on the television series "thirtysomething" and her work in film and TV dramas.
-
E.
Amanda Plummer
Amanda Plummer is an American actress known for her intense, eccentric character roles in films such as "Pulp Fiction" and "The Fisher King," as well as her work on stage and television.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e4e19881909879b394090d6629 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3000b21088190aa3ebb2ccbce9a6e |
completed | April 6, 2026, 12:36 a.m. |
Created at: March 30, 2026, 8:44 p.m.