Triple
T633773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saab AB |
E15976
|
entity |
| Predicate | keyProductType |
P7216
|
FINISHED |
| Object | fighter aircraft |
—
|
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: fighter aircraft | Statement: [Saab AB, keyProductType, fighter aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyProductType Context triple: [Saab AB, keyProductType, fighter aircraft]
-
A.
productFamily
Indicates that one product belongs to, or is categorized under, a broader product family or line.
-
B.
primaryProduct
chosen
Indicates that one entity is the main or most important product associated with, produced by, or offered by another entity.
-
C.
keyFeature
Indicates that something is a primary, distinguishing, or most important feature of an entity.
-
D.
keyHistoricalProduct
Indicates that the product played a significant or defining role in the historical development, identity, or evolution of the associated entity.
-
E.
scopeOfProducts
Indicates the range or extent of products that fall under a particular category, responsibility, or context.
- 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_69a4935c131c8190a5378c6bf101e8cc |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49ec3b6488190aa0dce216c089a2e |
completed | March 1, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69a49d030c648190ba1a02301b45f694 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.