Triple
T23101123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Big Steal |
E576032
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Ben Mendelsohn |
—
|
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 Mendelsohn | Statement: [The Big Steal, starring, Ben Mendelsohn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ben Mendelsohn Context triple: [The Big Steal, starring, Ben Mendelsohn]
-
A.
Ben Mendelsohn
chosen
Ben Mendelsohn is an Australian actor known for his intense character roles in film and television, including prominent villains in major Hollywood productions.
-
B.
Michael LaPaglia
Michael LaPaglia is an American actor and the brother of Australian actor Anthony LaPaglia.
-
C.
Jonathan LaPaglia
Jonathan LaPaglia is an Australian actor and television host best known for roles in series like "The District" and as the host of "Australian Survivor."
-
D.
Anthony LaPaglia
Anthony LaPaglia is an Australian actor best known for his Emmy-winning role on the television series "Without a Trace" and acclaimed performances in films such as "Lantana" and "Balibo."
-
E.
Guy Pearce
Guy Pearce is an Australian actor known for his versatile performances in films such as "Memento," "L.A. Confidential," and "The King's Speech."
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de8c5b4819095cddf989cade60d |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.