Triple
T26021970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thames Rowing Club |
E647173
|
entity |
| Predicate | hasKitElement |
P96799
|
FINISHED |
| Object | blades (oar design) |
—
|
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: blades (oar design) | Statement: [Thames Rowing Club, hasKitElement, blades (oar design)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKitElement Context triple: [Thames Rowing Club, hasKitElement, blades (oar design)]
-
A.
refersToKitElement
chosen
Indicates that one entity references or points to a specific element within a kit or predefined collection of components.
-
B.
hasElementType
Indicates that something is composed of or contains elements that are of a specified type.
-
C.
hasBruteElement
Indicates that an entity possesses or is associated with a raw, force-based, or brute-type elemental property.
-
D.
hasTechnicalElement
Indicates that something includes, involves, or is characterized by a technical component, feature, or aspect.
-
E.
hasExhibitElement
Indicates that something (such as an exhibit or display) includes or is composed of a particular element or component.
- 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_69e77e8aa65881909ca58918f29ab2a0 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f605e6cc1c8190a5379dbddee008a3 |
completed | May 2, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 9:04 a.m.