Triple
T22713219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Screamers |
E561655
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jennifer Rubin |
—
|
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: Jennifer Rubin | Statement: [Screamers, starring, Jennifer Rubin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jennifer Rubin Context triple: [Screamers, starring, Jennifer Rubin]
-
A.
Jennifer Rubin
chosen
Jennifer Rubin is an American actress and former fashion model best known for her roles in 1980s and 1990s horror and thriller films, including A Nightmare on Elm Street 3: Dream Warriors.
-
B.
Michelle Malkin
Michelle Malkin is an American conservative political commentator, author, and blogger known for her outspoken views on immigration and national security.
-
C.
Laura Klein
Laura Klein is a fictional character named Laura Klein who appears in the work titled "Fearless."
-
D.
Beth Fleisher
Beth Fleisher is a literary agent and former comic book editor known for her work in the science fiction and fantasy genres.
-
E.
Heidi Herzon
Heidi Herzon is a television producer best known for co-creating and producing the comedy series "The Sarah Silverman Program."
- 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_69e2454f1348819088d83f420925a5c1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790ab6208190a342f076002324ab |
completed | April 29, 2026, 3:20 a.m. |
Created at: April 17, 2026, 3:18 p.m.