Triple
T24902652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATP Cup |
E623620
|
entity |
| Predicate | matchComposition |
P32270
|
FINISHED |
| Object | two singles and one doubles rubber per tie |
—
|
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: two singles and one doubles rubber per tie | Statement: [ATP Cup, matchComposition, two singles and one doubles rubber per tie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchComposition Context triple: [ATP Cup, matchComposition, two singles and one doubles rubber per tie]
-
A.
matchStructure
chosen
Indicates that two entities share the same structural pattern or organization, regardless of their specific content or values.
-
B.
matchType
Indicates the specific category or nature of how two or more entities correspond or align with each other within a given context.
-
C.
matchesType
Indicates that one entity has the same or a compatible type as another entity according to a defined type system or classification.
-
D.
forcesComposition
Indicates that one entity compels or determines the structural makeup or arrangement of another entity.
-
E.
matchTypes
Indicates that two or more entities share the same type or category according to a specified classification.
- 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_69e2fac797cc8190b30d77f4121099ac |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f43043512481909501a3979cac9947 |
completed | May 1, 2026, 4:46 a.m. |
| PD | Predicate disambiguation | batch_69f420fd375c81908ea4a4e60b76ee8f |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:27 a.m.