Triple
T11666543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Photoplay |
E277263
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object | Photoplay |
E277263
|
NE FINISHED |
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: Photoplay | Statement: [Photoplay, hasTitle, Photoplay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Photoplay Context triple: [Photoplay, hasTitle, Photoplay]
-
A.
Photoplay magazine
chosen
Photoplay magazine was one of the earliest and most influential American fan magazines devoted to motion pictures and Hollywood stars.
-
B.
Screenwipe
Screenwipe is a British television review and satire series created and presented by Charlie Brooker that critiques TV programs, production practices, and media culture.
-
C.
Playbill
Playbill is an American theatre magazine best known for producing the official programs distributed at Broadway and other live stage productions.
-
D.
Variety
Variety is a leading American entertainment trade magazine and website known for its coverage of film, television, theater, and the broader media industry.
-
E.
Movie Magg
Movie Magg is a track featured on Paul McCartney’s rock and roll cover album "Run Devil Run."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a43f438081909da476294a057c38 |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef13b36ae4819096e6dfca23a69250 |
completed | April 27, 2026, 7:43 a.m. |
Created at: April 8, 2026, 9:39 p.m.