Triple
T2859924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Igor Stravinsky |
E63294
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Pulcinella |
E23980
|
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: Pulcinella | Statement: [Igor Stravinsky, notableWork, Pulcinella]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pulcinella Context triple: [Igor Stravinsky, notableWork, Pulcinella]
-
A.
Geppetto
Geppetto is a grieving woodcarver who creates the puppet Pinocchio and serves as a central emotional figure in Guillermo del Toro’s dark reimagining of the classic tale.
-
B.
Pierrot
chosen
Pierrot is a traditional stock character from French pantomime and commedia dell’arte, typically portrayed as a sad, white-faced clown in loose white clothing.
-
C.
Marcello
Marcello is a masculine given name of Italian origin, commonly used in Italy and other Romance-language countries.
-
D.
Jaquino
Jaquino is a supporting character in Beethoven’s opera "Fidelio," typically portrayed as the young jailer in love with Marzelline.
-
E.
Gobbo
Gobbo is a mischievous goblin character who serves as one of the main troublemaking antagonists in Enid Blyton’s Noddy stories.
- 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_69ab4c41e8c08190a9e8f5249cc12610 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf8aec3c8190a4168d8c916b5268 |
completed | March 7, 2026, 8:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b01d972aa481908f6cb5f27706990c |
completed | March 10, 2026, 1:33 p.m. |
Created at: March 6, 2026, 10:02 p.m.