Triple
T31025003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M-21 |
E790544
|
entity |
| Predicate | operationalCeilingClass |
P200520
|
FINISHED |
| Object | above 80,000 feet |
—
|
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: above 80,000 feet | Statement: [M-21, operationalCeilingClass, above 80,000 feet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operationalCeilingClass Context triple: [M-21, operationalCeilingClass, above 80,000 feet]
-
A.
operationalCeiling
Indicates the maximum altitude at which an entity (such as an aircraft or system) is designed or permitted to operate effectively and safely.
-
B.
operationalAltitude
Indicates the typical or designated altitude at which an entity is intended to operate.
-
C.
serviceCeiling_m_approx
Indicates an approximate value for an aircraft’s service ceiling, expressed in meters.
-
D.
operationalRange
Indicates the span of conditions (such as distance, time, or environment) within which a system, device, or process can function effectively and safely.
-
E.
operationalAltitudeBand
Indicates the range of altitudes within which an entity is intended or allowed to operate.
- 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_69f224c811508190a7de096a5b1f5798 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69ff9361943c81909544203cbc998a69 |
completed | May 9, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69ff913138a08190b59bdc9d8d199eb3 |
completed | May 9, 2026, 7:55 p.m. |
| PDg | Predicate description generation | batch_69ff935f48808190aa6f4834f59d45b8 |
completed | May 9, 2026, 8:04 p.m. |
Created at: April 29, 2026, 8:58 p.m.