Triple
T8687033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tenzing-Hillary Airport |
E206187
|
entity |
| Predicate | runwayEndFeature |
P75082
|
FINISHED |
| Object | cliff drop at one end |
—
|
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: cliff drop at one end | Statement: [Tenzing-Hillary Airport, runwayEndFeature, cliff drop at one end]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runwayEndFeature Context triple: [Tenzing-Hillary Airport, runwayEndFeature, cliff drop at one end]
-
A.
runwayEnd
Indicates that one entity represents the end point or terminus of a runway associated with the other entity.
-
B.
runwayCharacteristic
chosen
Indicates a relationship where specific attributes or features are associated with a runway.
-
C.
runwayEndHeading
Indicates the directional heading or bearing associated with the end of a runway, typically expressed in degrees relative to north.
-
D.
runway
Indicates a relationship where a runway serves as the takeoff and landing surface used by aircraft at an airport or airfield.
-
E.
runwaySurface
Indicates the type or condition of the surface material that a runway is made of or covered with.
- 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_69ca835481fc819084e33d3bc883bfa6 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5730309081909a9a0256c9bf5f8f |
completed | March 31, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69cc4569f9048190b9c86b4c81103d35 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:33 p.m.