Triple
T5105591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kherson Oblast |
E115083
|
entity |
| Predicate | cityOfKhersonLiberatedIn |
P36234
|
FINISHED |
| Object | November 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: November 2022 | Statement: [Kherson Oblast, cityOfKhersonLiberatedIn, November 2022]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityOfKhersonLiberatedIn Context triple: [Kherson Oblast, cityOfKhersonLiberatedIn, November 2022]
-
A.
liberatedCity
Indicates that an agent has freed a city from control, occupation, or oppression.
-
B.
wasFirstMajorTownLiberatedIn
Indicates that one entity was the first major town to be liberated in the context of a specified event or conflict.
-
C.
liberationPlace
chosen
Indicates the place or location where an entity was liberated or set free.
-
D.
countryLiberated
Indicates that one country has freed another country from occupation, control, or oppression, restoring its independence or autonomy.
-
E.
liberatedArea
Indicates that a particular area has been freed from control, occupation, or domination by a previously prevailing power or force.
- 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.