Triple
T11111179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Enter Air |
E262757
|
entity |
| Predicate | servesFrom |
P37780
|
FINISHED |
| Object | Polish regional airports |
—
|
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: Polish regional airports | Statement: [Enter Air, servesFrom, Polish regional airports]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesFrom Context triple: [Enter Air, servesFrom, Polish regional airports]
-
A.
servedFrom
chosen
Indicates that something is provided, delivered, or made available from a particular source or location.
-
B.
servesOn
Indicates that one entity performs duties, functions, or holds a role as a member within another entity, such as a group, body, or organization.
-
C.
servesUnder
Indicates that one entity works in a subordinate role under the authority, command, or supervision of another entity.
-
D.
servesUsersFrom
Indicates that an entity provides services or resources to users originating from or associated with a specified source or location.
-
E.
isServedOn
Indicates that one item (typically food or drink) is presented or provided atop or together with a particular surface, container, or accompaniment.
- 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_69d6aa9b46cc8190b19f9f0cc45bf322 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a6964508190b679303d3b3a4fd6 |
completed | April 9, 2026, 12:24 p.m. |
| PD | Predicate disambiguation | batch_69d7441cf8188190b8095f622c923156 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.