Triple
T19587401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yerevan Metro |
E470137
|
entity |
| Predicate | hasPlannedExtension |
P54844
|
FINISHED |
| Object | additional lines and stations in Yerevan |
—
|
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: additional lines and stations in Yerevan | Statement: [Yerevan Metro, hasPlannedExtension, additional lines and stations in Yerevan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlannedExtension Context triple: [Yerevan Metro, hasPlannedExtension, additional lines and stations in Yerevan]
-
A.
plannedExtensionTo
chosen
Indicates that one entity is intended or scheduled to be extended, expanded, or continued by another entity in the future.
-
B.
plannedExtensionLength
Indicates the intended or proposed length of an extension as specified in a plan or design.
-
C.
plannedExtensionDirection
Indicates the intended directional path or orientation along which something is planned to be extended in the future.
-
D.
hasPlannedPart
Indicates that one entity includes another entity as a component or segment within a planned or scheduled whole.
-
E.
hasExpansion
Indicates that one entity serves as a larger, extended, or elaborated form of another entity.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64052f61c81908bb49927d4246030 |
completed | April 20, 2026, 3:03 p.m. |
| PD | Predicate disambiguation | batch_69e514dbdb988190b55931a8138c73e7 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.