Triple
T2715074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nessun dorma |
E59948
|
entity |
| Predicate | sungByCharacter |
P14884
|
FINISHED |
| Object | Calaf |
E59946
|
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: Calaf | Statement: [Nessun dorma, sungByCharacter, Calaf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Calaf Context triple: [Nessun dorma, sungByCharacter, Calaf]
-
A.
Calaf
chosen
Calaf is the heroic prince in Giacomo Puccini's opera "Turandot," best known as the tenor role who sings the famous aria "Nessun dorma."
-
B.
Don José
Don José is the tragic soldier protagonist of Georges Bizet’s opera "Carmen," whose obsessive love for the title character leads to his downfall.
-
C.
Arturo
Arturo is a masculine given name of Spanish and Italian origin, equivalent to Arthur in English.
-
D.
Don Giovanni
Don Giovanni is a renowned opera by Wolfgang Amadeus Mozart that blends dark comedy and drama in the tale of the libertine nobleman Don Juan.
-
E.
Florestan
Florestan is the unjustly imprisoned political dissident whose rescue by his devoted wife Leonore drives the central drama of Beethoven’s opera "Fidelio."
- 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_69ab4ac92a088190bc74bca14038e3de |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda93a2388190b55a1c821ef6bc64 |
completed | March 7, 2026, 7:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afbbbe621881909e153290394798d6 |
completed | March 10, 2026, 6:35 a.m. |
Created at: March 6, 2026, 9:55 p.m.