Triple
T28126470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caproni Ca.32 |
E710940
|
entity |
| Predicate | developedFromSeries |
P1245
|
FINISHED |
| Object | early Caproni bomber designs |
—
|
LITERAL 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: early Caproni bomber designs | Statement: [Caproni Ca.32, developedFromSeries, early Caproni bomber designs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developedFromSeries Context triple: [Caproni Ca.32, developedFromSeries, early Caproni bomber designs]
-
A.
developedFrom
chosen
Indicates that one entity originates, evolves, or is derived from another as its source or precursor.
-
B.
developedSeries
Indicates that one entity is responsible for creating or developing a particular series associated with the other entity.
-
C.
formerSeries
Indicates that one entity was previously a series associated with another entity, but no longer holds that status.
-
D.
wasLaterDevelopedBy
Indicates that something (such as an idea, product, or work) was created or further developed at a later time by a specified agent or entity.
-
E.
laterExpandedIntoSeries
Indicates that an original work was subsequently developed or extended into a multi-part series.
- F. None of above.
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_69ef9b73bd288190a21ae3d6aa14f386 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 27, 2026, 9:20 p.m.