Triple
T17589716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Under-Secretary of State for War |
E428411
|
entity |
| Predicate | isMinisterialLevelOf |
P57228
|
FINISHED |
| Object | junior 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: junior minister | Statement: [Under-Secretary of State for War, isMinisterialLevelOf, junior minister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isMinisterialLevelOf Context triple: [Under-Secretary of State for War, isMinisterialLevelOf, junior minister]
-
A.
hasMinisterialRank
chosen
Indicates that an entity holds a position or status equivalent to a government minister in rank.
-
B.
methodOfMinistry
Indicates the specific way or approach through which ministry or religious service is carried out.
-
C.
typeOfMinister
Indicates the specific governmental or religious office or role that a particular minister holds.
-
D.
hasMinisterTitle
Indicates that an entity holds or is associated with a specific ministerial title or office.
-
E.
hasMinisterialSeat
Indicates that a governmental or administrative body holds its official ministerial seat or headquarters at a particular location.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e469e62d5c81909134e30a6d0f2e20 |
completed | April 19, 2026, 5:36 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fff0348190b899a32da537eaca |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:51 a.m.