Triple
T20805254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurricane Ophelia (2005) |
E512137
|
entity |
| Predicate | landInteraction |
P116019
|
FINISHED |
| Object | brushed the U.S. East Coast |
—
|
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: brushed the U.S. East Coast | Statement: [Hurricane Ophelia (2005), landInteraction, brushed the U.S. East Coast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: landInteraction Context triple: [Hurricane Ophelia (2005), landInteraction, brushed the U.S. East Coast]
-
A.
landComponent
Indicates that one entity is a physical land portion or segment that forms part of a larger land area or land-related whole.
-
B.
landAction
chosen
Indicates an action in which an entity comes down to and makes contact with a surface or ground, typically concluding a movement through air or space.
-
C.
landVariant
Indicates that one landform, terrain type, or land-related entity is an alternative or variant form of another.
-
D.
landRelation
Indicates a spatial or ownership-based relationship between entities and a specific piece or area of land.
-
E.
landPolicy
Indicates a relationship where an authority defines or applies rules governing the ownership, use, management, or distribution of land.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2cf1cbc819092d92625dfb107d0 |
completed | April 21, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69e5c99ca55481908e8d434fa901cfd6 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:40 p.m.