Triple
T26877048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | US-ARCOM |
E676779
|
entity |
| Predicate | commendationType |
P166166
|
FINISHED |
| Object | commendation medal |
—
|
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: commendation medal | Statement: [US-ARCOM, commendationType, commendation medal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commendationType Context triple: [US-ARCOM, commendationType, commendation medal]
-
A.
recommendation
Indicates that one entity suggests, endorses, or advises another entity as suitable or beneficial for a particular purpose or context.
-
B.
recommendationProcess
Indicates the process by which one entity evaluates options and suggests a preferred choice or course of action to another entity.
-
C.
recommendationHorizon
Indicates the time span into the future for which a recommendation or forecast is intended to remain relevant or valid.
-
D.
canRecommend
Indicates that one entity is able or authorized to suggest or endorse another entity as suitable or preferable.
-
E.
recommendedIn
Indicates that one entity is suggested or endorsed within the context, content, or scope of another entity (such as a document, list, or recommendation source).
- 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_69eee9bb44988190b6e11652d028bc59 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f66003a3f48190a2ba6da5aafbb5cb |
completed | May 2, 2026, 8:35 p.m. |
| PD | Predicate disambiguation | batch_69f65c1f94ac8190bc6fbc7916fc0d82 |
completed | May 2, 2026, 8:18 p.m. |
| PDg | Predicate description generation | batch_69f65f75ac608190a62cd6afce14f68e |
completed | May 2, 2026, 8:32 p.m. |
Created at: April 27, 2026, 5:36 a.m.