Triple
T17396678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safran Aircraft Engines |
E422971
|
entity |
| Predicate | designs |
P1529
|
FINISHED |
| Object | Silvercrest |
—
|
NE NERFINISHED |
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: Silvercrest | Statement: [Safran Aircraft Engines, designs, Silvercrest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Silvercrest Context triple: [Safran Aircraft Engines, designs, Silvercrest]
-
A.
Silvercrest
chosen
Silvercrest is a turbofan aircraft engine developed by Safran Aircraft Engines for business jets, known for its advanced fuel efficiency and reduced emissions.
-
B.
Silvermist
Silvermist is a water-talent fairy from Disney's Tinker Bell franchise, known for her gentle, optimistic personality and close friendship with Tinker Bell.
-
C.
Sylver
Sylver is a Belgian Eurodance and trance music group known for early-2000s club hits like "Turn the Tide" and "Forgiven."
-
D.
Silver Lady
Silver Lady is a nostalgic nickname evoking the streamlined elegance and scenic luxury of the historic California Zephyr passenger train.
-
E.
Ruby Crest
Ruby Crest is a prominent high-elevation ridge and hiking destination within Nevada’s Ruby Mountains, known for its alpine scenery and rugged terrain.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889d710288190bf0f4762801fefae |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43abd9b748190bd55c863276d9e3a |
completed | April 19, 2026, 2:15 a.m. |
Created at: April 10, 2026, 5:45 a.m.