Triple
T21766612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Thirteenth Hour (1947 film) |
E537308
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Mark Dennis |
—
|
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: Mark Dennis | Statement: [The Thirteenth Hour (1947 film), hasCastMember, Mark Dennis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Dennis Context triple: [The Thirteenth Hour (1947 film), hasCastMember, Mark Dennis]
-
A.
Mark Dennis
chosen
Mark Dennis was an actor known for his role in the 1947 mystery film "The Thirteenth Hour."
-
B.
Martin Dennis
Martin Dennis is a British television director best known for his work on popular sitcoms such as "Men Behaving Badly."
-
C.
Steve Dennis
Steve Dennis is a writer best known for co-authoring the memoir "Fallin’ Up: My Story."
-
D.
Dave Dennison
Dave Dennison is a fictional character associated with Dani Dennison in the Hocus Pocus film universe, depicted as a member of her family.
-
E.
David Denny
David Denny was a 19th-century American pioneer and early settler of Seattle, Washington, who played a key role in the city's founding and development.
- 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_69e0c46f5d1c8190bf830409e98464e5 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031aa9c888190887c5c1d1e3bab9f |
completed | April 28, 2026, 4:03 a.m. |
Created at: April 16, 2026, 6:51 p.m.