Triple
T33089003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British aircraft industry |
E846717
|
entity |
| Predicate | producedEngine |
P19271
|
FINISHED |
| Object | Rolls-Royce Merlin |
—
|
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: Rolls-Royce Merlin | Statement: [British aircraft industry, producedEngine, Rolls-Royce Merlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: producedEngine Context triple: [British aircraft industry, producedEngine, Rolls-Royce Merlin]
-
A.
developedEngine
Indicates that one entity created, designed, or engineered an engine for another entity or purpose.
-
B.
producedModel
Indicates that one entity created, manufactured, or generated the other entity as a model or product.
-
C.
aircraftEngineTypeProduced
chosen
Indicates that a particular type of aircraft engine is manufactured or produced by a specified entity.
-
D.
originatesFromEngine
Indicates that something has its source, cause, or production in a particular engine.
-
E.
plannedEngineModel
Indicates that an engine model has been selected or designated as the one intended to be used or implemented in a future plan or configuration.
- 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_69f3495590dc8190aa04f3dec74ce976 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fe163a41a0819098403b470e327d29 |
completed | May 8, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fe1358db5c819092570814a37ef5bd |
completed | May 8, 2026, 4:46 p.m. |
Created at: May 1, 2026, 1:26 a.m.