Triple
T22900993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hanscom Field |
E568316
|
entity |
| Predicate | hasRunway |
P105
|
FINISHED |
| Object | Runway 11/29 |
—
|
NE NERFINISHED |
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: Runway 11/29 | Statement: [Hanscom Field, hasRunway, Runway 11/29]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 11/29 Context triple: [Hanscom Field, hasRunway, Runway 11/29]
-
A.
Runway 11/29
Runway 11/29 is a principal paved runway at Volgograd International Airport in Russia, used for handling the airport’s commercial air traffic.
-
B.
Runway 11/29
chosen
Runway 11/29 is a primary paved runway at Worcester Regional Airport in Massachusetts, used for commercial and general aviation operations.
-
C.
Runway 11/29
Runway 11/29 is a primary paved runway at Schaumburg Regional Airport in Illinois, serving general aviation aircraft for takeoffs and landings.
-
D.
Runway 11/29
Runway 11/29 is a primary paved runway at Ercan International Airport in Northern Cyprus, used for handling the airport’s commercial air traffic operations.
-
E.
Runway 11/29
Runway 11/29 is a primary paved runway at Curaçao International Airport used for handling commercial and other aircraft operations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1801626488190b7e8ce3301667987 |
completed | April 29, 2026, 3:50 a.m. |
Created at: April 17, 2026, 3:41 p.m.