Triple
T20294668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Mouse That Roared |
E510115
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Benjamin Frankel |
—
|
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: Benjamin Frankel | Statement: [The Mouse That Roared, musicBy, Benjamin Frankel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Benjamin Frankel Context triple: [The Mouse That Roared, musicBy, Benjamin Frankel]
-
A.
Benjamin Frankel
chosen
Benjamin Frankel was a 20th-century British composer best known for his film scores and contributions to modern classical music.
-
B.
Eli Frankel
Eli Frankel is a television producer best known for creating the reality makeover series "Revenge Body with Khloé Kardashian."
-
C.
Benjamin Levin
Benjamin Levin is a television writer best known for his work on animated series such as "Adventure Time" and "Craig of the Creek."
-
D.
Etan Frankel
Etan Frankel is a television writer and producer known for his work on series such as Shameless and other acclaimed TV dramas.
-
E.
Sam Frankel
Sam Frankel was an American businessman best known for establishing Manheim Auctions, which grew into one of the world’s largest wholesale vehicle auction companies.
- 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_69e0b4c652388190b782cad965e5a098 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6770714c4819080e3256325747ebf |
completed | April 20, 2026, 6:57 p.m. |
Created at: April 16, 2026, 11:13 a.m.