Triple
T21543054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marooned |
E531542
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Nancy Kovack |
—
|
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: Nancy Kovack | Statement: [Marooned, starring, Nancy Kovack]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nancy Kovack Context triple: [Marooned, starring, Nancy Kovack]
-
A.
Nancy Kovack
chosen
Nancy Kovack is an American actress best known for her film and television roles in the 1960s, including appearances in "Jason and the Argonauts" and various popular TV series.
-
B.
Nancy Wyman
Nancy Wyman is an American Democratic politician who served as the 108th lieutenant governor of Connecticut and previously chaired the state’s Democratic Party.
-
C.
Nancy Berg
Nancy Berg was an American model and actress who appeared in film and television productions during the mid-20th century.
-
D.
Vicki Sirotta
Vicki Sirotta is a film producer best known for her work on the horror-thriller movie "The Prophecy."
-
E.
Nancy Blansky
Nancy Blansky is the central character of the 1970s American sitcom "Blansky's Beauties," portrayed as a seasoned Las Vegas showbiz professional managing a troupe of young performers.
- 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.