Triple
T355549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Garnett |
E7533
|
entity |
| Predicate | enteredNBADirectlyFrom |
P11649
|
FINISHED |
| Object | high school |
—
|
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 school | Statement: [Kevin Garnett, enteredNBADirectlyFrom, high school]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enteredNBADirectlyFrom Context triple: [Kevin Garnett, enteredNBADirectlyFrom, high school]
-
A.
allowedNBAPlayersFrom
Indicates that certain NBA players are permitted or eligible to come from a specified source, such as a team, region, or category.
-
B.
NBAdebutYear
Indicates the year in which a person first played in an official NBA game.
-
C.
draftedUnder
Indicates that one entity was formally selected or conscripted into a role, position, or service according to the authority, rules, or jurisdiction of another entity.
-
D.
joinedNBASeason
Indicates the season in which an individual first entered and began playing in the NBA.
-
E.
playedCollegeBasketballFor
Indicates that a person was a member of and competed for a specific college or university’s basketball team.
- 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ebad8bf08190b4a38ffd9157d641 |
completed | Feb. 28, 2026, 1:20 p.m. |
| PD | Predicate disambiguation | batch_69a2e9589e7c8190b2d3af8f858c96af |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea0b23ec8190bef9d593162388a4 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.