Triple
T1974190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trans States Airlines |
E42870
|
entity |
| Predicate | operatedServiceType |
P5884
|
FINISHED |
| Object | feeder 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: feeder flights | Statement: [Trans States Airlines, operatedServiceType, feeder flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatedServiceType Context triple: [Trans States Airlines, operatedServiceType, feeder flights]
-
A.
operatesService
chosen
Indicates that an agent runs, manages, or provides a particular service.
-
B.
operatesServiceTo
Indicates that one entity runs or provides a transportation or service route to another entity or location.
-
C.
operatesBy
Indicates that an entity performs its function, action, or process through the use or application of another entity (e.g., a method, mechanism, or principle).
-
D.
serviceOf
Indicates that one entity performs, provides, or fulfills a function or duty on behalf of another entity.
-
E.
operatedAs
Indicates that an entity functioned or was used in the capacity, role, or identity of another entity for some period of time.
- 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_69a8871289048190b00b0d7744b7b2b1 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb3f6c4208190a41e02733faed8df |
completed | March 7, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69abaff9a09c8190a81fa13f4b85bc79 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:36 p.m.