Triple
T22171514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skyscraper Souls |
E547929
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | William Axt |
—
|
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: William Axt | Statement: [Skyscraper Souls, musicBy, William Axt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Axt Context triple: [Skyscraper Souls, musicBy, William Axt]
-
A.
William Axt
chosen
William Axt was an American composer and conductor best known for his orchestral scores for early Hollywood silent and sound films.
-
B.
Herbert Woods
Herbert Woods is best known as the husband of renowned American harpist and businesswoman Sylvia Woods.
-
C.
Walter Rosen
Walter Rosen was a philanthropist and music patron best known for establishing the Caramoor estate as a cultural center for music and the arts.
-
D.
Charles J. Hitch
Charles J. Hitch was an American economist and defense analyst who served as president of the University of California after a prominent career in government and academia.
-
E.
John A. Cherberg
John A. Cherberg was a long-serving Washington State politician and former college football coach who became the state’s longest-tenured lieutenant governor.
- 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_69e11e3d53f88190a2b690e3f25bb062 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a68c26c8190b1258595bd96cb63 |
completed | April 28, 2026, 9:45 p.m. |
Created at: April 16, 2026, 8:34 p.m.