Triple
T17084496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Altered States |
E414559
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | John Corigliano |
E1172974
|
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: John Corigliano | Statement: [Altered States, composer, John Corigliano]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Corigliano Context triple: [Altered States, composer, John Corigliano]
-
A.
John Corigliano
chosen
John Corigliano is an American composer renowned for his innovative orchestral, chamber, and film music, including his Academy Award–winning score for "The Red Violin."
-
B.
William Bolcom
William Bolcom is an American composer and pianist known for his eclectic style that blends classical music with popular and cabaret influences.
-
C.
John Harbison
John Harbison is an American composer renowned for his orchestral, chamber, choral, and operatic works, and for his influential role in contemporary classical music.
-
D.
Aaron Jay Kernis
Aaron Jay Kernis is a Pulitzer Prize–winning American composer known for his vividly expressive, stylistically diverse orchestral and chamber works.
-
E.
Christopher Rouse
Christopher Rouse is an American film editor known for his work on high-octane action movies, including several entries in the Bourne franchise.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbe60d588190963ccd4c86af1233 |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fbe1d4c81909ce7e4626516b51d |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:35 a.m.