Triple
T22840442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | To the Bone |
E566064
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Fil Eisler |
—
|
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: Fil Eisler | Statement: [To the Bone, musicBy, Fil Eisler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fil Eisler Context triple: [To the Bone, musicBy, Fil Eisler]
-
A.
Fil Eisler
chosen
Fil Eisler is a Czech-born British composer best known for his work on film and television scores, including series like "Revenge" and "Empire."
-
B.
Fritz Peter
Fritz Peter was a mathematician best known for co-formulating the Peter–Weyl theorem, a foundational result in the representation theory of compact topological groups.
-
C.
Josef Gingold
Josef Gingold was a renowned 20th-century violinist and influential pedagogue, celebrated for his refined musicianship and for mentoring many leading violinists.
-
D.
Karl Haas
Karl Haas was a German-American classical music radio host and musicologist best known for his long-running program "Adventures in Good Music."
-
E.
Leo Zuckermann
Leo Zuckermann is the protagonist of the time-travel comedy series "Making History," a history professor who uses a duffel bag time machine to journey between the present and the American Revolution.
- 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e83fa48819084568264ef45c833 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:35 p.m.