Triple
T14978968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaplan turbine |
E373525
|
entity |
| Predicate | runnerBladeCount |
P36030
|
FINISHED |
| Object | typically 3 to 8 blades |
—
|
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: typically 3 to 8 blades | Statement: [Kaplan turbine, runnerBladeCount, typically 3 to 8 blades]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runnerBladeCount Context triple: [Kaplan turbine, runnerBladeCount, typically 3 to 8 blades]
-
A.
hasBladeCountPerTurbine
chosen
Indicates the number of blades associated with each individual turbine.
-
B.
hasStandardToeCount
Indicates that an entity possesses the typical or expected number of toes for its kind.
-
C.
tierCount
Indicates the number of distinct levels, ranks, or layers associated with an entity in a hierarchical or tiered structure.
-
D.
hasNumberOfSpokes
Indicates the relationship that specifies how many spokes are present in or associated with an object.
-
E.
hasEyelets
Indicates that an object possesses one or more eyelets (small holes or rings typically used for threading or fastening).
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6fcebf481909f72cab577560d82 |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a6169b48190a679609febd2d0e3 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:51 a.m.