Triple
T32005763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Gates |
E817261
|
entity |
| Predicate | commendation |
P166166
|
FINISHED |
| Object | highly commended officer within Central Police |
—
|
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: highly commended officer within Central Police | Statement: [Tony Gates, commendation, highly commended officer within Central Police]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commendation Context triple: [Tony Gates, commendation, highly commended officer within Central Police]
-
A.
recommendation
Indicates that one entity suggests, endorses, or advises another entity as suitable or beneficial for a particular purpose or context.
-
B.
commendationType
chosen
Indicates the specific category or kind of commendation associated with an action or relationship.
-
C.
recommendationProcess
Indicates the process by which one entity evaluates options and suggests a preferred choice or course of action to another entity.
-
D.
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).
-
E.
canRecommend
Indicates that one entity is able or authorized to suggest or endorse another entity as suitable or preferable.
- 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_69f348f8ce388190ae84376b1f348f12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f74062b9388190b30546cf700a825c |
completed | May 3, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69f73c802b848190b61a416b7488bd96 |
completed | May 3, 2026, 12:16 p.m. |
Created at: May 1, 2026, 12:15 a.m.