Triple
T37787615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baku–Tbilisi–Ceyhan pipeline |
E941995
|
entity |
| Predicate | transportsFromRegion |
P2059
|
FINISHED |
| Object | Caspian Sea region |
—
|
NE NERFINISHED |
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: Caspian Sea region | Statement: [Baku–Tbilisi–Ceyhan pipeline, transportsFromRegion, Caspian Sea region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transportsFromRegion Context triple: [Baku–Tbilisi–Ceyhan pipeline, transportsFromRegion, Caspian Sea region]
-
A.
transportationRegion
Indicates that one entity serves as, or is associated with, a geographic region relevant to the transportation activities or coverage of another entity.
-
B.
transports
chosen
Indicates that one entity carries or conveys another entity from one place to another.
-
C.
transportHubType
Indicates the specific category or kind of transport hub associated with an entity (e.g., airport, train station, bus terminal).
-
D.
transportsProperty
Indicates that one entity moves or carries a property or asset from one place or entity to another.
-
E.
transportHubScope
Indicates the extent or range of areas, routes, or services that a particular transport hub covers or connects.
- 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_69f76ee5cb0c81909a363d1c929156c0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ffcf46fd688190907fd1ceb499a8d1 |
completed | May 10, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69ffccde2a8c81908e055e74077dbd19 |
completed | May 10, 2026, 12:10 a.m. |
Created at: May 3, 2026, 4:19 p.m.