Triple
T24819226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Division of Bennelong |
E621013
|
entity |
| Predicate | formerPrimeMinisterRepresented |
P136997
|
FINISHED |
| Object | John Howard |
—
|
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: John Howard | Statement: [Division of Bennelong, formerPrimeMinisterRepresented, John Howard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerPrimeMinisterRepresented Context triple: [Division of Bennelong, formerPrimeMinisterRepresented, John Howard]
-
A.
primeMinisterRepresented
Indicates that a person served as the prime minister acting on behalf of, or in an official representative capacity for, a specific country, state, or governing body.
-
B.
formerPrimeMinister
chosen
Indicates that the subject once held the position of prime minister of the object entity but no longer does.
-
C.
formerPrimeMinisterMP
Indicates that a person served as a prime minister in the past and also held a position as a member of parliament.
-
D.
lastPrimeMinister
Indicates that the subject is the most recent individual to have held the office of prime minister of the object entity.
-
E.
representedByPrimeMinister
Indicates that one entity serves as the prime minister who officially represents another entity (such as a country, government, or organization).
- 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_69e2fabfd4648190bd0e5c7f4dbb6cab |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f627aedf548190bc9f53c8a2d67b50 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f623a4e1048190bbb8dd1253fdcee9 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 18, 2026, 5:04 a.m.