Triple
T21543053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marooned |
E531542
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Lee Grant |
—
|
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: Lee Grant | Statement: [Marooned, starring, Lee Grant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lee Grant Context triple: [Marooned, starring, Lee Grant]
-
A.
Lee Grant
chosen
Lee Grant is an Academy Award–winning American actress and director known for her powerful film and television performances and later work as a documentarian.
-
B.
Shirley Heath
Shirley Heath is a large open heathland and recreational green space located in the Shirley area of the West Midlands, England.
-
C.
Piper Laurie
Piper Laurie was an acclaimed American actress known for her intense performances in films like "Carrie" and "The Hustler" and the TV series "Twin Peaks."
-
D.
Diane Ladd
Diane Ladd is an American actress, director, and producer known for her acclaimed film and television roles, including her Academy Award–nominated performances and frequent collaborations with her daughter, Laura Dern.
-
E.
Carroll Baker
Carroll Baker is an American actress best known for her provocative breakout role in "Baby Doll" (1956) and a series of notable performances in 1950s and 1960s Hollywood films.
- 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_69e0c45f17148190949c330ab9c27706 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eeb58c34808190b0eb54ba01e2cc13 |
completed | April 27, 2026, 1:02 a.m. |
Created at: April 16, 2026, 6:28 p.m.