Triple
T9098337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arsenic and Old Lace (play) |
E218085
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Mortimer Brewster |
E215299
|
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: Mortimer Brewster | Statement: [Arsenic and Old Lace (play), mainCharacter, Mortimer Brewster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mortimer Brewster Context triple: [Arsenic and Old Lace (play), mainCharacter, Mortimer Brewster]
-
A.
Mortimer Brewster
chosen
Mortimer Brewster is the frantic, increasingly unhinged drama critic protagonist of the dark comedy film "Arsenic and Old Lace," who discovers his seemingly sweet aunts are serial poisoners.
-
B.
Ralph Winters
Ralph Winters was a film editor known for his work on numerous Hollywood movies across several decades.
-
C.
William Hathaway
William Hathaway was a Democratic U.S. Senator and Representative from Maine who served in Congress during the 1960s and 1970s.
-
D.
Samuel Dexter
Samuel Dexter was an American statesman who served as U.S. Secretary of War and Secretary of the Treasury in the early 19th century.
-
E.
Henry Richards
Henry Richards was the husband of American author Laura E. Richards, known primarily in relation to her life and work.
- 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_69ca83d9844081908e561e367fda6d45 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc970f340881909f5551219f151acf |
completed | April 1, 2026, 3:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d01824ee2081909cc5e6ae33fab2e5 |
completed | April 3, 2026, 7:42 p.m. |
Created at: March 30, 2026, 7:15 p.m.