Triple
T34386998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macquarie Harbour |
E882580
|
entity |
| Predicate | historicalPeriodOfPenalUse |
P72798
|
FINISHED |
| Object | early 19th century |
—
|
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: early 19th century | Statement: [Macquarie Harbour, historicalPeriodOfPenalUse, early 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalPeriodOfPenalUse Context triple: [Macquarie Harbour, historicalPeriodOfPenalUse, early 19th century]
-
A.
historicalPeriodOfPenalColony
chosen
Indicates the historical time period during which a given penal colony was in operation or existed.
-
B.
historicalPeriodOfUse
Indicates the time period during which something was in active use or commonly utilized.
-
C.
historicalPeriodOfNotableUse
Indicates the historical time period during which the entity was notably or most prominently used.
-
D.
historicalPeriodOfGreatestUse
Indicates the time period during which something was used most intensively or prevalently.
-
E.
historicalPeriodOfPrisonCamps
Indicates the historical time period during which the prison camps existed or were in operation.
- 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_69f349c0219881909393bbbc1edc8161 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0061454944819088a0babfe60f69fc |
completed | May 10, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_6a0060b9ee108190b91e8d99a16f2b30 |
completed | May 10, 2026, 10:40 a.m. |
Created at: May 1, 2026, 1:59 a.m.