Triple
T198774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norwegian flag |
E4054
|
entity |
| Predicate | crossOffset |
P4824
|
FINISHED |
| Object | towards hoist |
—
|
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: towards hoist | Statement: [Norwegian flag, crossOffset, towards hoist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossOffset Context triple: [Norwegian flag, crossOffset, towards hoist]
-
A.
offsets
Indicates that one entity counterbalances, compensates for, or reduces the effect, value, or impact of another.
-
B.
crossType
Indicates a relationship where one entity intersects, passes over, or traverses another, typically implying movement or extension across a boundary, area, or medium.
-
C.
crossedBy
Indicates that one entity (typically a path, line, or boundary) is intersected or traversed by another entity.
-
D.
usesOffsetFrom
chosen
Indicates that one entity determines or expresses its position, value, or behavior relative to another by applying a specified offset from that reference.
-
E.
cumulativeOffset
Indicates the total positional displacement of an entity relative to a reference point, obtained by summing all individual offsets along the path from that reference.
- 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_69a254bca59881909a15e1496f1508c7 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a25be47ea881909c296b30a0d47a65 |
completed | Feb. 28, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69a25b47481c8190add47c641c977bb9 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:44 a.m.