Triple
T36862954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyiv–Halych |
E910992
|
entity |
| Predicate | historicallyUnites |
P7838
|
FINISHED |
| Object | Kyiv |
—
|
NE NERFINISHED |
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: Kyiv | Statement: [Kyiv–Halych, historicallyUnites, Kyiv]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicallyUnites Context triple: [Kyiv–Halych, historicallyUnites, Kyiv]
-
A.
oftenUnitedWith
Indicates that two entities are frequently joined, combined, or associated together as a common or recurring unit.
-
B.
politicalEntityHistorically
Indicates that a political entity held a particular status, role, or relationship during a past historical period, but not necessarily in the present.
-
C.
historicalPeriodOfUnification
Indicates the historical time span during which separate entities were unified into a single political or organizational whole.
-
D.
wasUnifiedWith
chosen
Indicates that two or more previously separate entities were brought together to form a single unified whole.
-
E.
historicalFormation
Indicates the process or circumstances through which something came into existence or took shape over time in history.
- 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_69f76e80f6f0819091cba8e19b269615 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a015ff02814819094806517fc4c69fa |
completed | May 11, 2026, 4:49 a.m. |
| PD | Predicate disambiguation | batch_6a0154ddd3c48190b85f9f48731cfd8f |
completed | May 11, 2026, 4:02 a.m. |
Created at: May 3, 2026, 4:13 p.m.