Triple
T8833712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romania–Ukraine maritime boundary case |
E210209
|
entity |
| Predicate | concernsZone |
P41970
|
FINISHED |
| Object | continental shelf |
—
|
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: continental shelf | Statement: [Romania–Ukraine maritime boundary case, concernsZone, continental shelf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: concernsZone Context triple: [Romania–Ukraine maritime boundary case, concernsZone, continental shelf]
-
A.
concernsRegion
Indicates that something is about, relates to, or is specifically associated with a particular geographic or administrative region.
-
B.
concernsLocation
chosen
Indicates that something is about, related to, or focused on a particular location or place.
-
C.
concernsLayer
Indicates that something is related or pertains specifically to a particular layer within a layered structure or system.
-
D.
concernsSet
Indicates that something is about, relates to, or involves a particular set as its primary subject or focus.
-
E.
concernsProblem
Indicates that something is about, related to, or deals with a particular problem or issue.
- 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_69ca8388549c819095fd94eadefbb007 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60670fa48190b2a873f6498de7f6 |
completed | April 1, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69cc5c23d08481908d8c9b0ad3d1dc00 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:47 p.m.