Triple
T34557629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tachikawa Ki-74 |
E887248
|
entity |
| Predicate | intendedServiceCeiling |
P2095
|
FINISHED |
| Object | high altitude |
—
|
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 altitude | Statement: [Tachikawa Ki-74, intendedServiceCeiling, high altitude]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedServiceCeiling Context triple: [Tachikawa Ki-74, intendedServiceCeiling, high altitude]
-
A.
serviceCeiling_m_approx
Indicates an approximate value for an aircraft’s service ceiling, expressed in meters.
-
B.
serviceCeilingFeet
Indicates the maximum altitude, measured in feet, at which an aircraft or vehicle can effectively operate or provide service.
-
C.
operationalCeiling
chosen
Indicates the maximum altitude at which an entity (such as an aircraft or system) is designed or permitted to operate effectively and safely.
-
D.
maximumService
Indicates that an entity provides the highest allowable or achievable level of service within a given context or system.
-
E.
maximumCeiling
Indicates the highest allowable or achievable limit or value that something cannot exceed.
- 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_69f349d0c4d881908dd0950f5eb9ec0a |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fda94697c4819081291967202248be |
completed | May 8, 2026, 9:13 a.m. |
| PD | Predicate disambiguation | batch_69fda5973fcc8190a57daef31fb70a49 |
completed | May 8, 2026, 8:57 a.m. |
Created at: May 1, 2026, 2:02 a.m.