Triple
T30695027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Statue of Captain James Cook in Sydney |
E781433
|
entity |
| Predicate | mountingStructure |
P57768
|
FINISHED |
| Object | sandstone pedestal |
—
|
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: sandstone pedestal | Statement: [Statue of Captain James Cook in Sydney, mountingStructure, sandstone pedestal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mountingStructure Context triple: [Statue of Captain James Cook in Sydney, mountingStructure, sandstone pedestal]
-
A.
mountingInterface
chosen
Indicates that one entity serves as the surface, structure, or connection point onto which another entity is mounted or attached.
-
B.
mountingLocation
Indicates the physical position or surface on which something is attached, fixed, or installed.
-
C.
trainMounting
Indicates a relationship where an entity is boarding or getting onto a train.
-
D.
hostStructure
Indicates that one structure serves as the host or containing framework for another structure.
-
E.
mountType
Indicates the manner or configuration in which one object is mounted or attached to 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_69f224ab24e08190991d6edb6df58e8b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 8:34 p.m.