Triple
T5300073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Napier Sabre |
E119954
|
entity |
| Predicate | laterVariantsPower |
P37443
|
FINISHED |
| Object | over 3,000 horsepower |
—
|
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: over 3,000 horsepower | Statement: [Napier Sabre, laterVariantsPower, over 3,000 horsepower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterVariantsPower Context triple: [Napier Sabre, laterVariantsPower, over 3,000 horsepower]
-
A.
poweredVersionOf
chosen
Indicates that one entity is a more powerful, enhanced, or upgraded version of another entity.
-
B.
laterVariantRole
Indicates that one role is a subsequent or later variant of another, reflecting a modified or evolved version of the original role.
-
C.
laterVersion
Indicates that one entity is a subsequent or more recent version of another entity in a version sequence.
-
D.
famousVariant
Indicates that one entity is a well-known or widely recognized version or form of another entity.
-
E.
weakenedVariantsInclude
Indicates that a set of weakened or attenuated forms of something (e.g., a virus, argument, or feature) contains or encompasses the specified variant.
- 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_69bd446f22b88190b6a47fb91c68a3e7 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd8e44e7c881909b241b2fec366038 |
completed | March 20, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69bd845097ac81909678624c4907fda4 |
completed | March 20, 2026, 5:30 p.m. |
Created at: March 20, 2026, 1:53 p.m.