Triple
T33347817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julian Savea |
E853846
|
entity |
| Predicate | scoringRate |
P157414
|
FINISHED |
| Object | high try-per-game ratio for All Blacks |
—
|
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: high try-per-game ratio for All Blacks | Statement: [Julian Savea, scoringRate, high try-per-game ratio for All Blacks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scoringRate Context triple: [Julian Savea, scoringRate, high try-per-game ratio for All Blacks]
-
A.
scoring
Indicates the act of achieving points or a measurable result, typically by successfully completing an action that contributes to a score or outcome.
-
B.
scoringRecord
Indicates that there exists a record documenting a scoring event or outcome associated with the given entities.
-
C.
scoringType
Indicates the method or criteria by which performance, outcomes, or results are evaluated and assigned a score in a given context.
-
D.
scoringAverage
chosen
Indicates the typical or mean score achieved by an entity over a series of attempts, events, or performances.
-
E.
scoringUnit
Indicates that one entity functions as a unit or component responsible for scoring or assigning scores to another entity.
- 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_69f3496a1a588190bad9cbe9221144e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e3156ea48190b604e414665ef351 |
completed | May 3, 2026, 5:54 a.m. |
| PD | Predicate disambiguation | batch_69f6de0b9ba48190887c9eb5d06a2e94 |
completed | May 3, 2026, 5:32 a.m. |
Created at: May 1, 2026, 1:34 a.m.