Triple
T12022468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Perekop (1944) |
E286186
|
entity |
| Predicate | aimOfSide2 |
P85506
|
FINISHED |
| Object | Hold land access to Crimea |
—
|
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: Hold land access to Crimea | Statement: [Battle of Perekop (1944), aimOfSide2, Hold land access to Crimea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aimOfSide2 Context triple: [Battle of Perekop (1944), aimOfSide2, Hold land access to Crimea]
-
A.
side2
Indicates that an entity is positioned on, associated with, or corresponds to the second side of another entity or structure.
-
B.
aimOfOtherSide
chosen
Indicates that one party’s goal or intended outcome is directed toward or defined in relation to the opposing or counterpart side in a relationship or interaction.
-
C.
side2Strength
Indicates the magnitude or level of strength associated with the second side in a relationship, comparison, or interaction.
-
D.
onSide
Indicates that one entity is positioned along or adjacent to the side of another entity.
-
E.
secondaryGoal
Indicates that something serves as a subordinate or supporting objective in addition to a primary goal.
- 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_69d6ab4669e48190b59246358b0383ab |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902b6ebbc8190b13c44a61c6f81b9 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:47 p.m.