Triple
T31542153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caroline Evers-Swindell |
E804773
|
entity |
| Predicate | typeOfRowing |
P201250
|
FINISHED |
| Object | sculling |
—
|
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: sculling | Statement: [Caroline Evers-Swindell, typeOfRowing, sculling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfRowing Context triple: [Caroline Evers-Swindell, typeOfRowing, sculling]
-
A.
typeOfRower
Indicates that one entity is a specific kind or category of rower in relation to another entity.
-
B.
hasRowingSide
Indicates that an entity involved in rowing is associated with a specific side (e.g., port or starboard) on which it rows.
-
C.
isRowingCompanionOf
Indicates that one entity accompanies another in the activity of rowing, typically sharing a boat or rowing effort together.
-
D.
hasRowingCourse
Indicates that one entity provides or includes a rowing course for another entity or at a given location.
-
E.
isOlympicRowingCourse
Indicates that a location functions as an officially designated course used for Olympic rowing competitions.
- 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_69f348d11a048190a65eb8384a3754ac |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ffe12ee59c8190bc7da386e6d5332d |
completed | May 10, 2026, 1:36 a.m. |
| PD | Predicate disambiguation | batch_69ffe0a138bc8190a3d4b48cd579e985 |
completed | May 10, 2026, 1:34 a.m. |
| PDg | Predicate description generation | batch_69ffe12d61e0819098692270ab2625e3 |
completed | May 10, 2026, 1:36 a.m. |
Created at: April 30, 2026, 10:06 p.m.