Triple
T24753649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mekoryuk Airport |
E619217
|
entity |
| Predicate | serves function |
P43607
|
FINISHED |
| Object | delivery of supplies |
—
|
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: delivery of supplies | Statement: [Mekoryuk Airport, serves function, delivery of supplies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serves function Context triple: [Mekoryuk Airport, serves function, delivery of supplies]
-
A.
mayServeFunction
Indicates that one entity is capable of performing, fulfilling, or acting in the role of a specified function for another entity or context.
-
B.
describesFunctionOf
Indicates that one entity explains, defines, or specifies the functional role or purpose of another entity.
-
C.
providesFunctionalityOf
Indicates that one entity supplies, implements, or makes available the capabilities or functions that are normally associated with another entity.
-
D.
servesUse
chosen
Indicates that one entity is used by or functions to serve the purpose or needs of another entity.
-
E.
servesFeature
Indicates that one entity provides or makes available a particular feature or functionality to 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_69e2fabb349881908a13a212a0221a63 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f5ffc74fa481909b4fe24a9337f9eb |
completed | May 2, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69f5f7f99dc08190afcfb3bc4dfbec1d |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 18, 2026, 4:25 a.m.