Triple
T37370829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heer (German Army) |
E927836
|
entity |
| Predicate | militaryBranchColor |
P15387
|
FINISHED |
| Object | white Waffenfarbe for infantry |
—
|
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: white Waffenfarbe for infantry | Statement: [Heer (German Army), militaryBranchColor, white Waffenfarbe for infantry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryBranchColor Context triple: [Heer (German Army), militaryBranchColor, white Waffenfarbe for infantry]
-
A.
corpsColour
chosen
Indicates the specific color associated with a military corps or unit.
-
B.
regimentalColourSymbol
Indicates that something serves as the symbolic emblem or design used on a regiment’s official flag or standard.
-
C.
corpsInsignia
Indicates that one entity serves as the official emblem, badge, or insignia representing a particular corps or military branch associated with another entity.
-
D.
militaryBranchAssociatedWith
Indicates a relationship where an entity is connected to, or operates as part of, a specific branch of a military organization.
-
E.
militaryBranchAbbreviation
Indicates the standard shortened form or acronym used to represent a specific branch of a military organization.
- 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd3a69f1e08190a11aed015bff0858 |
completed | May 8, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_69fd39124180819080ca7911d3515d6d |
completed | May 8, 2026, 1:14 a.m. |
Created at: May 3, 2026, 4:16 p.m.