Triple
T36544418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Public Defence Service (New Zealand) |
E901102
|
entity |
| Predicate | underpinsRight |
P3636
|
FINISHED |
| Object | right to a fair trial |
—
|
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: right to a fair trial | Statement: [Public Defence Service (New Zealand), underpinsRight, right to a fair trial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underpinsRight Context triple: [Public Defence Service (New Zealand), underpinsRight, right to a fair trial]
-
A.
underpins
chosen
Indicates that one entity serves as the fundamental basis, support, or justification for another.
-
B.
underlies
Indicates that one entity serves as a fundamental basis, support, or underlying cause for another entity, condition, or phenomenon.
-
C.
holdsUnder
Indicates that one entity maintains possession, control, or validity of another entity subject to certain conditions, constraints, or a specific context.
-
D.
unterliegt
Indicates that one entity is subject to, governed or constrained by the authority, rules, influence, or control of another entity.
-
E.
supportedRight
Indicates that one entity endorsed, upheld, or actively backed the right or entitlement held by 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_69f76e61217081908b79d610fe67b013 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd783fed9c81909e792702636c4f1f |
completed | May 8, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_69fd7788e63c81909de22fdafcfe41c0 |
completed | May 8, 2026, 5:41 a.m. |
Created at: May 3, 2026, 4:11 p.m.