Triple
T36970240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dutch ship Leeuwin |
E914543
|
entity |
| Predicate | chartedFeature |
P191926
|
FINISHED |
| Object | southwest coastline of Australia |
—
|
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: southwest coastline of Australia | Statement: [Dutch ship Leeuwin, chartedFeature, southwest coastline of Australia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chartedFeature Context triple: [Dutch ship Leeuwin, chartedFeature, southwest coastline of Australia]
-
A.
chartedIn
Indicates that something is recorded, mapped, or documented within a particular chart, diagram, or graphical representation.
-
B.
namedFeature
Indicates that an entity has a specific feature or attribute that is explicitly given a name.
-
C.
crestFeature
Indicates that an entity possesses a notable crest-related characteristic or structural feature.
-
D.
throughFeature
Indicates that one entity is connected to, accessed, or achieved by means of a particular feature or characteristic of another entity.
-
E.
destinationFeature
Indicates the feature, place, or element that serves as the endpoint or target location of a movement, transfer, or directed relation.
- F. None of above. chosen
Provenance (4 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
| PDg | Predicate description generation | batch_69fcef636dfc819085cf91323f2e4edd |
completed | May 7, 2026, 8 p.m. |
Created at: May 3, 2026, 4:14 p.m.