Triple
T20116878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arthur Marx |
E490488
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Gummo Marx |
—
|
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: Gummo Marx | Statement: [Arthur Marx, relative, Gummo Marx]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gummo Marx Context triple: [Arthur Marx, relative, Gummo Marx]
-
A.
Gummo Marx
chosen
Gummo Marx was an American vaudeville performer and the least publicly known of the Marx Brothers, who left show business early to serve in World War I and later became a successful theatrical agent.
-
B.
Harpo Marx
Harpo Marx was an American comedian and silent, harp-playing member of the Marx Brothers, famed for his wordless, anarchic performances in classic early 20th-century films.
-
C.
Charlot
Charlot is a French surname borne by various notable individuals, including artists and public figures.
-
D.
Groucho Marx
Groucho Marx was an American comedian and film star famed for his quick wit, distinctive greasepaint mustache and glasses, and his role in classic Marx Brothers comedies.
-
E.
Zeppo Marx
Zeppo Marx was the youngest of the Marx Brothers, known for playing the straight man in their early films before leaving show business to become a successful engineer and inventor.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66739fde4819083e54f7435405bf0 |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:29 p.m.