Triple
T21480960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marnie Piper |
E529990
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Marnie Piper |
—
|
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: Marnie Piper | Statement: [Marnie Piper, fullName, Marnie Piper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marnie Piper Context triple: [Marnie Piper, fullName, Marnie Piper]
-
A.
Marnie Piper
chosen
Marnie Piper is the young witch protagonist of Disney's "Halloweentown" film series, known for discovering her magical heritage and defending the supernatural world.
-
B.
Moyna McGill
Moyna McGill was an Irish-born stage and film actress, best known as the mother of actress Angela Lansbury and for her supporting roles in British and American cinema in the mid-20th century.
-
C.
Amanda Dumfries
Amanda Dumfries is a key supporting character in the 2007 horror film "The Mist," portrayed as a young mother trapped in a supermarket when a mysterious, deadly fog engulfs her town.
-
D.
Elizabeth McRae
Elizabeth McRae is known primarily as the wife of influential television producer Sydney Newman, a key figure in British and Canadian TV history.
-
E.
Marnie Spencer
Marnie Spencer is a film editor known for her work on the 2016 fantasy adventure film "The BFG."
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea338f988190a3044f8d02a567fe |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.