Triple
T5105593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kherson Oblast |
E115083
|
entity |
| Predicate | claimedAnnexationDate |
P9024
|
FINISHED |
| Object | September 2022 |
—
|
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: September 2022 | Statement: [Kherson Oblast, claimedAnnexationDate, September 2022]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimedAnnexationDate Context triple: [Kherson Oblast, claimedAnnexationDate, September 2022]
-
A.
annexationDate
chosen
Indicates the date on which one entity formally annexed or incorporated another entity into its territory or jurisdiction.
-
B.
annexedInYear
Indicates that one entity was formally annexed or incorporated into another in the specified calendar year.
-
C.
annexedDuring
Indicates that one entity was formally incorporated into and brought under the control of another entity during a specified time period.
-
D.
preAnnexationCountry
Indicates that an entity was the country to which another entity belonged or was associated before an annexation took place.
-
E.
partialAnnexationBy
Indicates a relationship where one entity has annexed or incorporated only a portion of another entity’s territory, authority, or structure, rather than taking it over in full.
- 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_69bd4440b3348190be1251fd8b7951f1 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7589e40c8190a46e4a1b7142be14 |
completed | March 20, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69bd715e06808190931934dc9930f997 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:41 p.m.