Triple
T4573955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa national cricket team |
E123098
|
entity |
| Predicate | T20WorldCupBestResult |
P58023
|
FINISHED |
| Object | semi-finalist |
—
|
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: semi-finalist | Statement: [South Africa national cricket team, T20WorldCupBestResult, semi-finalist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: T20WorldCupBestResult Context triple: [South Africa national cricket team, T20WorldCupBestResult, semi-finalist]
-
A.
t20WorldCupWinner
Indicates that the subject is the team that won the ICC T20 Cricket World Cup in the specified edition or year.
-
B.
captainODI
Indicates that the subject serves as the captain of the object’s team in One Day International (ODI) cricket matches.
-
C.
mostWickets
Indicates that the subject holds the record for taking the highest number of wickets in a given cricket context or competition.
-
D.
firstT20IYear
Indicates the year in which an entity (typically a player or team) first participated in a Twenty20 International (T20I) match.
-
E.
mostWicketsTakenBy
Indicates the bowler who has taken the highest number of wickets in a given match, series, tournament, or time period.
- 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_69bd46466c7081909d07f36be2d08804 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd58c89a5c81909a78bf0ac64777ad |
completed | March 20, 2026, 2:25 p.m. |
| PD | Predicate disambiguation | batch_69bd5228b70c8190ac48705e35a710c1 |
completed | March 20, 2026, 1:56 p.m. |
| PDg | Predicate description generation | batch_69bd56b4a9508190acdb888eef18f1ee |
completed | March 20, 2026, 2:16 p.m. |
Created at: March 20, 2026, 1:10 p.m.