Triple
T5049321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Donetsk Airport |
E113744
|
entity |
| Predicate | involvedStructure |
P44908
|
FINISHED |
| Object | new terminal building of Donetsk International Airport |
—
|
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: new terminal building of Donetsk International Airport | Statement: [Battle of Donetsk Airport, involvedStructure, new terminal building of Donetsk International Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedStructure Context triple: [Battle of Donetsk Airport, involvedStructure, new terminal building of Donetsk International Airport]
-
A.
affectedStructure
chosen
Indicates that one entity is the structure, component, or part that is impacted, altered, or influenced by another entity or event.
-
B.
integratedStructure
Indicates that multiple components are combined into a single, cohesive structure that functions as an integrated whole.
-
C.
anatomicalFeature
Indicates that one entity is an anatomical part, structure, or feature of another entity.
-
D.
hasHumanStructure
Indicates that one entity possesses or exhibits a structural form or organization characteristic of humans.
-
E.
viaStructure
Indicates that one entity is connected to or accessed through a particular structural element or medium.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74249a8c8190952680aee06a9286 |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd715479f08190933604aebd34414f |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.