Triple
T35427583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galway Airport |
E1023960
|
entity |
| Predicate | primaryOperations |
P58201
|
FINISHED |
| Object | private flights |
—
|
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: private flights | Statement: [Galway Airport, primaryOperations, private flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryOperations Context triple: [Galway Airport, primaryOperations, private flights]
-
A.
primaryOperation
chosen
Indicates the main or most important operation performed or used by an entity in a given context.
-
B.
operatesPrimarilyOn
Indicates that one entity is mainly or chiefly used to act upon, affect, or process another entity.
-
C.
primaryModes
Indicates the main methods, forms, or channels through which something typically operates, is expressed, or is carried out.
-
D.
majorOperationsOf
Indicates that one entity is a primary or significant operation, activity, or functional undertaking associated with another entity.
-
E.
operations
Indicates that one entity performs, manages, or is responsible for the functional activities or processes of another entity.
- 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_69f76df6704081909900c60be10d5849 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0324d08190ac5b610cc0f6a38c |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:03 p.m.