Triple
T31422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Capitol Police |
E626
|
entity |
| Predicate | hasBadge |
P1617
|
FINISHED |
| Object | United States Capitol Police badge |
—
|
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: United States Capitol Police badge | Statement: [United States Capitol Police, hasBadge, United States Capitol Police badge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBadge Context triple: [United States Capitol Police, hasBadge, United States Capitol Police badge]
-
A.
hasTypeOfInsignia
chosen
Indicates that an entity bears or is associated with a specific kind or category of insignia.
-
B.
badgeShape
Indicates the geometric form or outline that a badge takes.
-
C.
badgeReverseDesign
Indicates the design or imagery that appears on the reverse (back) side of a badge.
-
D.
badgeObverseDesign
Indicates the design or imagery that appears on the front (obverse) side of a badge.
-
E.
hasBeard
Indicates that one entity possesses or displays a beard.
- 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a249ec0d288190ac3a0939db61813b |
completed | Feb. 28, 2026, 1:50 a.m. |
| PD | Predicate disambiguation | batch_69a24870417081909c7c01e400c94716 |
completed | Feb. 28, 2026, 1:44 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.