Triple
T23081935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Younis Khan |
E575496
|
entity |
| Predicate | hasBattingAverageType |
P110791
|
FINISHED |
| Object | high Test batting average |
—
|
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 Test batting average | Statement: [Younis Khan, hasBattingAverageType, high Test batting average]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBattingAverageType Context triple: [Younis Khan, hasBattingAverageType, high Test batting average]
-
A.
battingAverageType
Indicates the type or category of a batting average associated with a player or performance (e.g., season, career, situational).
-
B.
testBattingAverage
Indicates that an entity evaluates or measures the batting average performance of another entity or subject.
-
C.
battingAverage
Indicates the statistical relationship between a batter’s number of hits and official at-bats, expressing how often they successfully get a hit.
-
D.
battingAverageCategory
chosen
Indicates the classification of an entity’s batting average into a defined performance category (e.g., low, medium, high).
-
E.
odiBattingAverage
Indicates the batting average a player has achieved in One Day International (ODI) cricket matches.
- 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_69e245be28d48190ad1348d5a73db37d |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18da239e48190ad041261c6b510a0 |
completed | April 29, 2026, 4:48 a.m. |
| PD | Predicate disambiguation | batch_69ef89e5ce748190b2c3ac3843484127 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:56 p.m.