Triple
T323775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soviet military officers |
E6469
|
entity |
| Predicate | woreInsigniaType |
P1617
|
FINISHED |
| Object | shoulder boards |
—
|
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: shoulder boards | Statement: [Soviet military officers, woreInsigniaType, shoulder boards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: woreInsigniaType Context triple: [Soviet military officers, woreInsigniaType, shoulder boards]
-
A.
hasTypeOfInsignia
chosen
Indicates that an entity bears or is associated with a specific kind or category of insignia.
-
B.
hasInsigniaWornBy
Indicates that a particular insignia is worn by a specified entity (such as a person, group, or organization).
-
C.
isNonMilitaryDecoration
Indicates that an honor or award is a decoration that is not associated with military service or military institutions.
-
D.
authorizedHeadgear
Indicates that a particular item of headgear is officially permitted or approved for use in a given context or by a specific authority.
-
E.
hasOfficialInsigniaLocation
Indicates the specific place where an entity’s official insignia is physically located or displayed.
- 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_69a2e7933d6c8190bb2592ad13286ef2 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eb1a37c08190b1380f6bf8513a37 |
completed | Feb. 28, 2026, 1:18 p.m. |
| PD | Predicate disambiguation | batch_69a2e949364c8190bc2351f5413f5057 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.