Triple
T166723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamayev Kurgan memorial complex |
E3030
|
entity |
| Predicate | guardOfHonor |
P2354
|
FINISHED |
| Object | ceremonial guard at eternal flame |
—
|
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: ceremonial guard at eternal flame | Statement: [Mamayev Kurgan memorial complex, guardOfHonor, ceremonial guard at eternal flame]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardOfHonor Context triple: [Mamayev Kurgan memorial complex, guardOfHonor, ceremonial guard at eternal flame]
-
A.
honors
chosen
Indicates that one entity shows respect, recognition, or esteem toward another entity, often in a formal or ceremonial way.
-
B.
flagBearer
Indicates that one entity serves as the carrier or holder of a flag on behalf of another entity, group, or cause.
-
C.
commemoratedBy
Indicates that something is honored, remembered, or celebrated through a particular action, event, object, or representation.
-
D.
honourType
Indicates the specific category or classification of an honour or award associated with an entity.
-
E.
isNonMilitaryDecoration
Indicates that an honor or award is a decoration that is not associated with military service or military institutions.
- 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_69a2524ce1e48190ab066bf72859f474 |
completed | Feb. 28, 2026, 2:26 a.m. |
| NER | Named-entity recognition | batch_69a25884c8d88190bc4cb4e3541e8116 |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a25664ba8081908ac298511a9fc5ba |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:34 a.m.