Triple
T23052018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Vogues |
E574044
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Magic Town |
—
|
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: Magic Town | Statement: [The Vogues, notableWork, Magic Town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Magic Town Context triple: [The Vogues, notableWork, Magic Town]
-
A.
Magic Town
chosen
Magic Town is a 1947 American comedy film starring James Stewart as a pollster who exploits a statistically average small town, directed by William A. Wellman and written by Robert Riskin.
-
B.
Happy Town
Happy Town is an American mystery drama television series that follows a small town plagued by abductions and dark secrets.
-
C.
Tiny Town
Tiny Town is a miniature, child-sized city attraction where kids can explore scaled-down buildings, streets, and activities designed for imaginative play.
-
D.
Storyland
Storyland is a whimsical, fairy-tale themed children's playground and attraction located within New Orleans City Park.
-
E.
Storyland
Storyland is a film and television production company known for producing the mystery-thriller series "Wayward Pines."
- 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_69e245ba7ae48190be606dbc54120e39 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1867d010c8190bc5dba6758d0b797 |
completed | April 29, 2026, 4:18 a.m. |
Created at: April 17, 2026, 3:54 p.m.