Triple
T2359996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nakajima Ki-44 |
E47248
|
entity |
| Predicate | climbPerformance |
P38209
|
FINISHED |
| Object | high rate of climb |
—
|
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: high rate of climb | Statement: [Nakajima Ki-44, climbPerformance, high rate of climb]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: climbPerformance Context triple: [Nakajima Ki-44, climbPerformance, high rate of climb]
-
A.
climbingActivity
Indicates an activity where an entity ascends or scales a surface, structure, or natural formation, typically using physical effort and coordination.
-
B.
canClimb
Indicates that one entity has the ability or permission to climb another entity or surface.
-
C.
climbingClass
Indicates the difficulty or grade level assigned to a climbing route, problem, or activity.
-
D.
climbingDiscipline
Indicates the specific style or category of climbing practiced or associated with an entity (e.g., bouldering, sport, trad).
-
E.
totalAscent
Indicates the total cumulative elevation gained over the course of a movement, route, or activity.
- F. None of above. chosen
Provenance (4 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_69a88a1a4a6081908645b0f2914521ab |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc722ac3c819091f4316a4a166a77 |
completed | March 7, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69abc599b92c819093d9e15d4437705d |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc6a85e2c8190afec217ff29476be |
completed | March 7, 2026, 6:33 a.m. |
Created at: March 4, 2026, 7:55 p.m.