Triple
T37871537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Convair 580 |
E944616
|
entity |
| Predicate | powerplantUpgradeTo |
P193167
|
FINISHED |
| Object | Allison 501 turboprop engines |
—
|
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: Allison 501 turboprop engines | Statement: [Convair 580, powerplantUpgradeTo, Allison 501 turboprop engines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerplantUpgradeTo Context triple: [Convair 580, powerplantUpgradeTo, Allison 501 turboprop engines]
-
A.
powerplantUpgradeFrom
chosen
Indicates that a power plant has been upgraded or derived from a previous power plant configuration or installation.
-
B.
powerplantUpgradeComparedTo
Indicates a comparison between two entities regarding the extent or nature of an upgrade made to their power plants.
-
C.
powerplantAdvantage
Indicates that one power plant has an advantage or beneficial characteristic over another in a given context.
-
D.
powerplantVariant
Indicates that one power plant is a specific version, configuration, or model variant of another power plant design.
-
E.
powerplant
Indicates that an entity functions as a facility or installation where energy sources are converted into usable power, typically electricity.
- 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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fd3a69f1e08190a11aed015bff0858 |
completed | May 8, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_69fd39124180819080ca7911d3515d6d |
completed | May 8, 2026, 1:14 a.m. |
Created at: May 3, 2026, 4:19 p.m.