Triple
T29439669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TRACECA corridor |
E746674
|
entity |
| Predicate | typeOfConnectivity |
P194896
|
FINISHED |
| Object | intermodal connectivity |
—
|
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: intermodal connectivity | Statement: [TRACECA corridor, typeOfConnectivity, intermodal connectivity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfConnectivity Context triple: [TRACECA corridor, typeOfConnectivity, intermodal connectivity]
-
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.
connectivityScheme
chosen
Indicates the type or method of connection used between entities or components within a system.
-
C.
networkType
Indicates the category or kind of network associated with or used by an entity (e.g., wired, wireless, virtual, or specific protocol-based networks).
-
D.
connectivity
Indicates...the existence, degree, or quality of a link or communication pathway between entities, allowing interaction or information flow between them.
-
E.
connectorType
Indicates the specific kind or category of connection interface that links two entities.
- 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_69f0a7a180e48190ae775e40047dbcb5 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69ff14d596e88190be5263b7f96a96cd |
completed | May 9, 2026, 11:04 a.m. |
| PD | Predicate disambiguation | batch_69ff13f0208081909369aeb3b77a6b1f |
completed | May 9, 2026, 11:01 a.m. |
Created at: April 28, 2026, 3:20 p.m.