Triple
T12852439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russia–Ukraine maritime disputes |
E307357
|
entity |
| Predicate | relatedToYear |
P75923
|
FINISHED |
| Object | 2014 |
—
|
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: 2014 | Statement: [Russia–Ukraine maritime disputes, relatedToYear, 2014]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedToYear Context triple: [Russia–Ukraine maritime disputes, relatedToYear, 2014]
-
A.
relatedYear
Indicates a connection between an entity and a specific year that is relevant to its occurrence, validity, or significance.
-
B.
relatedTo
Indicates a general, non-specific relationship or association exists between two entities.
-
C.
associatedWithYearFilm
Indicates a relationship where something (such as an event, award, or record) is linked to or pertains to a specific film released or identified in a given year.
-
D.
hasAssociatedYear
chosen
Indicates that an entity is linked to a specific year that is relevant to it (e.g., creation, occurrence, or reference year).
-
E.
relationshipStartYear
Indicates the calendar year in which a particular relationship between entities was initiated.
- 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_69d7bdf5e7cc8190be357278bc5ba3bb |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9714208f881908f7f8a921362909a |
completed | April 10, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69d96fa3002881908000357b1f95a3ac |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:36 p.m.