Triple
T21933200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | At the Movies |
E541622
|
entity |
| Predicate | hasPresenter |
P83
|
FINISHED |
| Object | Ben Mankiewicz |
—
|
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: Ben Mankiewicz | Statement: [At the Movies, hasPresenter, Ben Mankiewicz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ben Mankiewicz Context triple: [At the Movies, hasPresenter, Ben Mankiewicz]
-
A.
Ben Mankiewicz
chosen
Ben Mankiewicz is an American television host and film critic best known as a longtime presenter and commentator on Turner Classic Movies (TCM).
-
B.
Don Mankiewicz
Don Mankiewicz was an American screenwriter and novelist known for his work in film and television during the mid-20th century.
-
C.
Jim Hecht
Jim Hecht is a television writer and producer best known for co-creating the HBO sports drama series "Winning Time: The Rise of the Lakers Dynasty."
-
D.
Tom Mankiewicz
Tom Mankiewicz was an American screenwriter, director, and producer best known for his work on several James Bond films and the script for the 1978 film "Superman."
-
E.
Oscar Paar
Oscar Paar is an individual notable enough to be recognized as a prominent bearer of the surname Paar.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12400a1248190b3f8f27f2aa4a858 |
completed | April 28, 2026, 9:17 p.m. |
Created at: April 16, 2026, 7:47 p.m.