Triple
T36017868
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tjukurla |
E1041895
|
entity |
| Predicate | locatedOnLandType |
P159560
|
FINISHED |
| Object | Aboriginal reserve land |
—
|
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: Aboriginal reserve land | Statement: [Tjukurla, locatedOnLandType, Aboriginal reserve land]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOnLandType Context triple: [Tjukurla, locatedOnLandType, Aboriginal reserve land]
-
A.
locatedOnIslandOrPeninsula
Indicates that something is situated on an island or on a peninsula, rather than on a mainland area.
-
B.
onLandmass
chosen
Indicates that one entity is physically located on or within the boundaries of a specified landmass.
-
C.
locatedOnCoastAt
Indicates that one entity is situated on the coastline at the specific location represented by another entity.
-
D.
landsAt
Indicates that a moving entity arrives and comes to rest at a specific location or destination.
-
E.
landerType
Indicates the specific kind or category of lander involved in the relationship or action.
- 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_69f76e2b981881908e4e160607fa82eb |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0895b48190acdd88dc10db7be7 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:07 p.m.