Triple
T14768932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McClure expedition |
E347076
|
entity |
| Predicate | traversalMethod |
P8588
|
FINISHED |
| Object | partly by sledge over ice |
—
|
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: partly by sledge over ice | Statement: [McClure expedition, traversalMethod, partly by sledge over ice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traversalMethod Context triple: [McClure expedition, traversalMethod, partly by sledge over ice]
-
A.
formerTraversal
Indicates that one entity previously traversed, passed through, or traveled along another entity, but is no longer doing so.
-
B.
alsoTraverses
Indicates that a route, path, or entity passes through or crosses an additional location or segment beyond its primary traversal.
-
C.
enablesTraversal
Indicates that one entity provides the means or capability for another entity to move through, across, or along something.
-
D.
navigatesUsing
chosen
Indicates that one entity moves or travels through an environment by relying on another entity as its means, tool, or method of navigation.
-
E.
travelsThrough
Indicates that something moves along, passes across, or is routed via a particular path, medium, or location.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec81236f081908063bb4350b7b985 |
completed | April 14, 2026, 11:04 p.m. |
| PD | Predicate disambiguation | batch_69de8c02e5c08190943c27594026faf7 |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:30 a.m.