Triple
T23018587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hold Back the Night |
E573101
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Richard Shannon |
—
|
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: Richard Shannon | Statement: [Hold Back the Night, castMember, Richard Shannon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Shannon Context triple: [Hold Back the Night, castMember, Richard Shannon]
-
A.
Richard Shannon
chosen
Richard Shannon was an American character actor known for his supporting roles in mid-20th-century films and television, often appearing in war and Western genres.
-
B.
Frank Shannon
Frank Shannon was an Irish-American character actor best known for his roles in early 20th-century films and serials, particularly in science fiction and adventure genres.
-
C.
Robert Shannon
Robert Shannon is the introspective Irish orphan who serves as the central coming-of-age protagonist in A. J. Cronin’s novel *The Green Years*.
-
D.
Sam Sharkey
Sam Sharkey is a character associated with the American folklore surrounding the legendary lumberjack Paul Bunyan.
-
E.
Michael Carnes
Michael Carnes is a screenwriter best known for co-writing the comedy film "Mr. Woodcock."
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.