Triple
T15105531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Assistant Minister for Defence |
E360778
|
entity |
| Predicate | supportsMinister |
P59601
|
FINISHED |
| Object | Minister for Defence |
—
|
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: Minister for Defence | Statement: [Assistant Minister for Defence, supportsMinister, Minister for Defence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsMinister Context triple: [Assistant Minister for Defence, supportsMinister, Minister for Defence]
-
A.
supportedMinistryOf
Indicates that one entity provided assistance, endorsement, or resources to help carry out the ministry or religious service activities of another entity.
-
B.
hasMinister
Indicates that one entity serves as the minister (political, religious, or administrative official) responsible for or associated with another entity.
-
C.
supportedMinistryIn
Indicates that an entity provided support to a ministry operating within a specified location or jurisdiction.
-
D.
supportsCommittee
Indicates that one entity provides backing, endorsement, or assistance to a committee.
-
E.
supportsOfficeHolder
chosen
Indicates that one entity backs, endorses, or provides assistance to a person currently holding a particular office or position.
- 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00588f35481909674f161bf0f3918 |
completed | April 15, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69deb96c1d9c81909351558ed97bc5b7 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:05 a.m.