Triple
T1651969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. Soffel |
E35711
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Matthew Modine |
E47801
|
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: Matthew Modine | Statement: [Mrs. Soffel, hasCastMember, Matthew Modine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matthew Modine Context triple: [Mrs. Soffel, hasCastMember, Matthew Modine]
-
A.
Matthew Modine
chosen
Matthew Modine is an American actor best known for his roles in films like "Full Metal Jacket" and the series "Stranger Things."
-
B.
Tom Berenger
Tom Berenger is an American actor best known for his roles in films such as "Platoon," "The Big Chill," and "Inception," often portraying tough, complex characters.
-
C.
Scott Glenn
Scott Glenn is an American actor known for his intense, rugged performances in films such as "The Right Stuff," "The Silence of the Lambs," and "Backdraft."
-
D.
Fred Ward
Fred Ward was an American character actor known for his rugged, everyman roles in films such as "Tremors," "The Right Stuff," and "Short Cuts."
-
E.
David Hennings
David Hennings is a film cinematographer known for his work on major studio comedies and other feature films, including "Horrible Bosses."
- 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_69a8860568888190a32cd9f70acbba42 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90a88cb108190a836b972f600c257 |
completed | March 5, 2026, 4:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad8abe91bc8190ba363e1f7fd07b9f |
completed | March 8, 2026, 2:42 p.m. |
Created at: March 4, 2026, 7:29 p.m.