Triple
T16839715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plum Island Airport |
E409374
|
entity |
| Predicate | isTypeOfField |
P121387
|
FINISHED |
| Object | non-towered airport |
—
|
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: non-towered airport | Statement: [Plum Island Airport, isTypeOfField, non-towered airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTypeOfField Context triple: [Plum Island Airport, isTypeOfField, non-towered airport]
-
A.
hasTypeOfField
chosen
Indicates that an entity possesses or is associated with a specific category or kind of field.
-
B.
isFixedFieldOf
Indicates that one element is a fixed, non-variable field or attribute that belongs to and is structurally defined as part of another entity.
-
C.
hasTypeOfReference
Indicates that one entity uses or is associated with a particular kind or category of reference (such as a citation, pointer, or referential link) to another entity.
-
D.
isClassOf
Indicates that one entity is a class or category to which another entity belongs or is an instance of.
-
E.
fieldType
Indicates the classification or category that defines the nature or kind of a given field within a structure or context.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b34f902c8190a334ba7caa04ce7e |
completed | April 18, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69e32b87b4248190aaddb05e88452356 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:23 a.m.