Triple
T8991002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RUH |
E214786
|
entity |
| Predicate | hasTerminalUse |
P43356
|
FINISHED |
| Object | international and domestic 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: international and domestic flights | Statement: [RUH, hasTerminalUse, international and domestic flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTerminalUse Context triple: [RUH, hasTerminalUse, international and domestic flights]
-
A.
usedTerminal
Indicates that an entity made use of or interacted with a particular terminal or endpoint device.
-
B.
hasTerminalFacility
Indicates that an entity possesses or includes a terminal facility used as an endpoint for transport, communication, or related operations.
-
C.
TerminalEUsedFor
chosen
Indicates that a terminal E is used for a particular purpose, function, or activity.
-
D.
hasTerminalFunction
Indicates that something possesses a function or role specifically associated with an endpoint, boundary, or final stage within a system or process.
-
E.
hasIntegratedTerminal
Indicates that one entity includes or supports a built-in terminal interface as part of its functionality.
- 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_69ca83a05c608190bdfdbdb25e994b39 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc68733548819096a5ba0ff41e43da |
completed | April 1, 2026, 12:36 a.m. |
| PD | Predicate disambiguation | batch_69cc5edba0f88190b97401636a076d7a |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:04 p.m.