Triple
T34077949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief Justice of New South Wales |
E873956
|
entity |
| Predicate | canAlsoSitOn |
P65248
|
FINISHED |
| Object | Court of Appeal of New South Wales |
—
|
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: Court of Appeal of New South Wales | Statement: [Chief Justice of New South Wales, canAlsoSitOn, Court of Appeal of New South Wales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canAlsoSitOn Context triple: [Chief Justice of New South Wales, canAlsoSitOn, Court of Appeal of New South Wales]
-
A.
canSitIn
Indicates that one entity is able or permitted to sit inside or occupy the seating space of another entity.
-
B.
canSitAt
Indicates that one entity is permitted or able to occupy a seating position at another entity (such as a place, object, or location).
-
C.
canSitWithout
Indicates that one entity is able to sit without the presence, support, or assistance of another entity.
-
D.
maySit
chosen
Indicates that one entity is permitted or allowed to sit on or in another entity.
-
E.
cannotSit
Indicates that an entity is unable or not allowed to sit on, in, or at another entity.
- 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_69f349a566808190a1c63b898f33cddf |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f70bd3d9408190b405c4fa07634ae7 |
completed | May 3, 2026, 8:48 a.m. |
| PD | Predicate disambiguation | batch_69f70ac0170c819098e3b8e41d02efef |
completed | May 3, 2026, 8:43 a.m. |
Created at: May 1, 2026, 1:52 a.m.