Triple
T2967205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Istria |
E80193
|
entity |
| Predicate | borderChangedIn |
P21193
|
FINISHED |
| Object | 1918 |
—
|
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: 1918 | Statement: [Istria, borderChangedIn, 1918]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderChangedIn Context triple: [Istria, borderChangedIn, 1918]
-
A.
borderChange
chosen
Indicates a change in the boundaries between geographic or political entities, such as when borders are redrawn, expanded, reduced, or otherwise altered over time.
-
B.
borderStraddling
Indicates that something (such as a feature, structure, or area) extends across and occupies territory on both sides of a border between two regions or jurisdictions.
-
C.
borderRegion
Indicates a region that lies along or near the boundary separating two distinct geographic or political areas.
-
D.
borderStateNearby
Indicates that one state is geographically close to, but does not necessarily directly touch, the border of another state.
-
E.
boundaryBetween
Indicates that something serves as a dividing line or limit separating two distinct regions, areas, or 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_69ad8b14ffe881908ffed62f9595c867 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad996e93788190ba9883714d4dfa0c |
completed | March 8, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69ad960e71f8819088179d11248c6ed0 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.