Triple
T34410003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NZX Derivatives Market |
E883229
|
entity |
| Predicate | underlying |
P130589
|
FINISHED |
| Object | New Zealand dairy products |
—
|
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: New Zealand dairy products | Statement: [NZX Derivatives Market, underlying, New Zealand dairy products]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: underlying Context triple: [NZX Derivatives Market, underlying, New Zealand dairy products]
-
A.
underlies
Indicates that one entity serves as a fundamental basis, support, or underlying cause for another entity, condition, or phenomenon.
-
B.
underpins
Indicates that one entity serves as the fundamental basis, support, or justification for another.
-
C.
underlyingData
chosen
Indicates that one entity serves as the foundational or source data upon which another entity is based, derived, or computed.
-
D.
under
Indicates that one entity is positioned below or beneath another entity, often implying vertical alignment or coverage.
-
E.
underlyingIssue
Indicates that one situation, problem, or condition is the fundamental cause or root problem behind another.
- 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_69f349c1f2208190a09a489bb8b2719d |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd35d108908190b79b1e8e6bbd62aa |
completed | May 8, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69fd34cb46108190b43c3b7f67ec4cd4 |
completed | May 8, 2026, 12:56 a.m. |
Created at: May 1, 2026, 1:59 a.m.