Triple
T32027476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supply Corps officers |
E817856
|
entity |
| Predicate | corpsInsignia |
P173137
|
FINISHED |
| Object | three oak leaves |
—
|
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: three oak leaves | Statement: [Supply Corps officers, corpsInsignia, three oak leaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: corpsInsignia Context triple: [Supply Corps officers, corpsInsignia, three oak leaves]
-
A.
wearsInsigniaAt
Indicates that an entity is wearing or displaying a particular insignia at a specified location or point in time.
-
B.
corpsColour
Indicates the specific color associated with a military corps or unit.
-
C.
rankInsigniaWornOn
Indicates the physical location on a uniform or body where a rank insignia is displayed or attached.
-
D.
isDistinctiveUnitInsignia
Indicates that one entity serves as the distinctive unit insignia (a unique identifying emblem or badge) associated with another entity, typically a military unit.
-
E.
regimentalBadgeFeature
Indicates that one entity serves as a design element or component featured on a regiment’s badge.
- F. None of above. chosen
Provenance (4 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_69f348fb04e4819081f4eab040ed7959 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b46ac390819092125a5e03b66b63 |
completed | May 3, 2026, 2:35 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
| PDg | Predicate description generation | batch_69f6b21da77081908c5c015c4606d344 |
completed | May 3, 2026, 2:25 a.m. |
Created at: May 1, 2026, 12:17 a.m.