Triple
T2430143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chancellor of the Duchy of Lancaster |
E52822
|
entity |
| Predicate | typicallyActsAs |
P24836
|
FINISHED |
| Object | senior adviser to the Prime Minister |
—
|
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: senior adviser to the Prime Minister | Statement: [Chancellor of the Duchy of Lancaster, typicallyActsAs, senior adviser to the Prime Minister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyActsAs Context triple: [Chancellor of the Duchy of Lancaster, typicallyActsAs, senior adviser to the Prime Minister]
-
A.
actsOnBehalfOf
Indicates that one entity performs actions or makes decisions as a representative or proxy for another entity.
-
B.
appearsAs
chosen
Indicates that one entity is presented, perceived, or manifested in the form, role, or guise of another entity.
-
C.
alsoServesAs
Indicates that one entity has an additional role, function, or identity that it fulfills simultaneously with its primary one.
-
D.
actsOn
Indicates that one entity performs an action that affects, targets, or is directed toward another entity.
-
E.
isAssociatedWith
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
- 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_69ab4959bcc0819083246f9fb10439e3 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abcc74a5108190a3a9631b0cc1a127 |
completed | March 7, 2026, 6:57 a.m. |
| PD | Predicate disambiguation | batch_69abc5aa1b60819081b87f7985c6cff3 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 6, 2026, 9:43 p.m.