Triple
T19922440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rewa Airport |
E478830
|
entity |
| Predicate | hasPlannedConnectivityRole |
P61597
|
FINISHED |
| Object | enhance air connectivity for Rewa |
—
|
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: enhance air connectivity for Rewa | Statement: [Rewa Airport, hasPlannedConnectivityRole, enhance air connectivity for Rewa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlannedConnectivityRole Context triple: [Rewa Airport, hasPlannedConnectivityRole, enhance air connectivity for Rewa]
-
A.
connectivityMode
Indicates how two or more entities are linked or able to communicate with each other, such as the type or method of connection used between them.
-
B.
connectsRole
chosen
Indicates a relationship in which one entity is linked to another by assigning or associating a specific role between them.
-
C.
hasPlannedAccess
Indicates that an entity is expected or scheduled to have access to another entity or resource in the future, according to a plan or arrangement.
-
D.
hasPlannedTerminalType
Indicates that an entity is associated with a specific type of terminal that is intended or scheduled to be used in the future.
-
E.
hasPlatformsConnectedBy
Indicates that two or more platforms are linked together by some connecting structure or mechanism.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c6919c8190a96106532580b6b6 |
completed | April 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69e537f070b481908958e0e5911dcdc1 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:53 p.m.