Triple
T23834726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Herbert Ministry |
E589616
|
entity |
| Predicate | officeHeldByLeader |
P105869
|
FINISHED |
| Object | Premier of Queensland |
—
|
NE NERFINISHED |
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: Premier of Queensland | Statement: [First Herbert Ministry, officeHeldByLeader, Premier of Queensland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeHeldByLeader Context triple: [First Herbert Ministry, officeHeldByLeader, Premier of Queensland]
-
A.
officeHeldByMembers
Indicates that a particular office or position is held by one or more members of a specified group or organization.
-
B.
officeHeldByMember
Indicates that a specific office or position is held or occupied by a particular member.
-
C.
officeHeldByDecisionMaker
Indicates that a particular official position or office is occupied by the decision maker involved in a given decision or action.
-
D.
officeHeldByActor
Indicates that a specific office, position, or role is held or occupied by a particular actor.
-
E.
officeHeldByHeadOfGovernmentOrState
chosen
Indicates the specific official position or role that is occupied by a given head of government or head of state.
- 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_69e25d1922d481909cab567c06a802ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c7f8811c8190b40ae04ec3fa1ee3 |
completed | April 29, 2026, 8:57 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 8:07 p.m.