Triple
T4044448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princeton Tigers men’s rowing |
E84030
|
entity |
| Predicate | rowClass |
P53777
|
FINISHED |
| Object | heavyweight |
—
|
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: heavyweight | Statement: [Princeton Tigers men’s rowing, rowClass, heavyweight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rowClass Context triple: [Princeton Tigers men’s rowing, rowClass, heavyweight]
-
A.
positionClass
Indicates the classification or category assigned to an entity based on its role, rank, or position within a defined structure or system.
-
B.
heightClass
Indicates the categorical height level or range to which an entity is assigned (e.g., short, medium, tall).
-
C.
viewsAsLeadingClass
Indicates that one entity regards another entity as the primary or dominant class within a given context or classification system.
-
D.
titleHolderClass
Indicates the class or category of entity that holds or bears a particular title.
-
E.
dominantClass
Indicates that one class or category holds primary authority, influence, or precedence over others within a given context.
- 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_69aed930bd5c819083e7dcc14fc44f69 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb5f85d48190ba80a0a24fbe438a |
completed | March 9, 2026, 4:54 p.m. |
| PD | Predicate disambiguation | batch_69aef900386481909d04555a9ec9b0e3 |
completed | March 9, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69aef98ed84c81909dc86097df4afd4f |
completed | March 9, 2026, 4:47 p.m. |
Created at: March 9, 2026, 3:37 p.m.