Triple
T33431617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japan vs South Africa (2015 Rugby World Cup) |
E856144
|
entity |
| Predicate | SouthAfricaConversions |
P179082
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [Japan vs South Africa (2015 Rugby World Cup), SouthAfricaConversions, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SouthAfricaConversions Context triple: [Japan vs South Africa (2015 Rugby World Cup), SouthAfricaConversions, 3]
-
A.
conversionPlace
Indicates the location where one entity is transformed, converted, or changed into another form or state.
-
B.
conversionDetails
Indicates the specific parameters, conditions, and outcomes associated with transforming one entity, state, or value into another.
-
C.
convertedUnit
Indicates that one unit is the result of converting a quantity expressed in another unit.
-
D.
conversionUse
Indicates that one entity is used as a means, method, or context for converting another entity from one form, state, or representation to another.
-
E.
freelyConvertible
Indicates that one entity can be exchanged or converted into another without restrictions, limitations, or significant barriers.
- 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_69f349709e7881908c342b4d34f555f4 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69f71c33edac8190a59f6ff19b265fc5 |
completed | May 3, 2026, 9:58 a.m. |
Created at: May 1, 2026, 1:36 a.m.