Triple
T8388413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WTA 250 tournaments |
E197877
|
entity |
| Predicate | categoryHierarchy |
P56442
|
FINISHED |
| Object | below WTA 500 tournaments |
—
|
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: below WTA 500 tournaments | Statement: [WTA 250 tournaments, categoryHierarchy, below WTA 500 tournaments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: categoryHierarchy Context triple: [WTA 250 tournaments, categoryHierarchy, below WTA 500 tournaments]
-
A.
categoryStructure
chosen
Indicates the hierarchical or organizational relationship that defines how categories are structured and arranged relative to one another.
-
B.
catalogCategory
Indicates that an item or entity is assigned to, or belongs within, a specific catalog category.
-
C.
orderHierarchy
Indicates a hierarchical ordering relationship where one entity is positioned above or below another in a structured sequence or chain of command.
-
D.
categoryDefinedIn
Indicates that a category is formally specified or established within a particular source, context, or definitional framework.
-
E.
titleHierarchy
Indicates a hierarchical relationship between titles, where one title is ranked above or below another in an ordered structure.
- 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_69ca82f749388190bffbea6dfb509016 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb81090f688190a3a8d1680383c361 |
completed | March 31, 2026, 8:08 a.m. |
| PD | Predicate disambiguation | batch_69cb70cfe82881909fe374ba52649e84 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:03 p.m.