Triple
T31758333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Sydney By-laws |
E810612
|
entity |
| Predicate | areMadeUnder |
P156610
|
FINISHED |
| Object | University of Sydney Act 1989 (NSW) |
—
|
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: University of Sydney Act 1989 (NSW) | Statement: [University of Sydney By-laws, areMadeUnder, University of Sydney Act 1989 (NSW)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areMadeUnder Context triple: [University of Sydney By-laws, areMadeUnder, University of Sydney Act 1989 (NSW)]
-
A.
madeUnderAct
chosen
Indicates that something was created, established, or carried out in accordance with a specific legal act or statute.
-
B.
madeBy
Indicates that something is created, produced, or brought into existence by a particular agent or source.
-
C.
isUsedUnder
Indicates that one entity is utilized or applied within the context, conditions, or framework defined by another entity.
-
D.
makerOf
Indicates that one entity is the creator, producer, or manufacturer of another entity.
-
E.
usesMake
Indicates that one entity employs, applies, or utilizes another entity as a means, tool, or method to achieve some purpose.
- 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_69f348e340d48190b780fae618c51464 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ab7ee7248190888c22161b3ce235 |
completed | May 3, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69f6aa21f2508190a204a424ffc00ca6 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:30 p.m.