Triple
T13426318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rally New Zealand |
E313490
|
entity |
| Predicate | notableStageSurface |
P1242
|
FINISHED |
| Object | gravel roads |
—
|
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: gravel roads | Statement: [Rally New Zealand, notableStageSurface, gravel roads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableStageSurface Context triple: [Rally New Zealand, notableStageSurface, gravel roads]
-
A.
notableSurface
Indicates that one entity is a surface or exterior of particular significance or prominence in relation to another entity.
-
B.
notableStage
Indicates that an entity is recognized as an important or distinguished stage or phase in relation to another entity or process.
-
C.
surfaceType
chosen
Indicates the kind or classification of surface associated with an entity or interaction.
-
D.
notableTargetArea
Indicates that an action, effect, or focus is specifically directed toward a particularly important or prominent area or region.
-
E.
surfaceFeatureOf
Indicates that one entity is a surface-level characteristic, pattern, or feature belonging to or present on 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_69d806ad0c44819088833ae1ec9e9690 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaed1f9208190bf5ef5b8a7ded376 |
completed | April 12, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69d9a03926188190ab3948d1f5d3941f |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:40 p.m.