Triple
T4460015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rolls-Royce Pegasus |
E98227
|
entity |
| Predicate | hasNozzles |
P21647
|
FINISHED |
| Object | two cold (fan) nozzles |
—
|
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: two cold (fan) nozzles | Statement: [Rolls-Royce Pegasus, hasNozzles, two cold (fan) nozzles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNozzles Context triple: [Rolls-Royce Pegasus, hasNozzles, two cold (fan) nozzles]
-
A.
numberOfNozzles
chosen
Indicates the quantity of nozzles associated with or present on a given entity.
-
B.
doesNotProduce
Indicates that one entity fails to generate, create, or yield another entity or outcome.
-
C.
hasNoPowerOver
Indicates that one entity lacks authority, control, or influence over another entity or situation.
-
D.
hasSpray
Indicates that one entity possesses, contains, or is equipped with a spray or spraying capability in relation to another entity or context.
-
E.
hasNumberOfPins
Indicates that an entity is associated with a specific count of pins it possesses or uses.
- 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_69b3454a7c608190944f5455c8031d73 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35673337c8190b923159791ec27e3 |
completed | March 13, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69b34f649df081909d3cc2f6a1b8f282 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:33 p.m.