Triple
T19455193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Halloween (1978 film) |
E486716
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Nancy Loomis |
—
|
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 Loomis | Statement: [Halloween (1978 film), starring, Nancy Loomis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nancy Loomis Context triple: [Halloween (1978 film), starring, Nancy Loomis]
-
A.
Nancy Loomis
chosen
Nancy Loomis is an American actress best known for her roles in John Carpenter’s horror films, including "Halloween" and "Assault on Precinct 13."
-
B.
Daniel Myrick
Daniel Myrick is an American filmmaker best known as the co-writer and co-director of the influential found-footage horror film "The Blair Witch Project."
-
C.
Diane Becker
Diane Becker is a film producer best known for her work on the Oscar-winning documentary "Navalny," which chronicles Russian opposition leader Alexei Navalny.
-
D.
Donna Peele
Donna Peele is an American former model best known for her brief mid-1990s marriage to actor Charlie Sheen.
-
E.
Lee Russell
Lee Russell was an American photographer known for his work documenting rural life and poverty in the United States as part of the Farm Security Administration project during the Great Depression.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633c2b1108190b492ca23487b91f8 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:38 p.m.