Triple
T9601157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Smart |
E231852
|
entity |
| Predicate | NBASportsmanshipAward |
P79375
|
FINISHED |
| Object | 2019–20 |
—
|
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: 2019–20 | Statement: [Marcus Smart, NBASportsmanshipAward, 2019–20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: NBASportsmanshipAward Context triple: [Marcus Smart, NBASportsmanshipAward, 2019–20]
-
A.
NBAMostValuablePlayerAward
Indicates that an entity has received the NBA Most Valuable Player (MVP) award for a particular season.
-
B.
NBAAllSportsmanshipAwardSeason
chosen
Indicates that a particular NBA season is associated with the NBA Sportsmanship Award being given in that season.
-
C.
NBAMostImprovedPlayerAward
Indicates that an entity has received the NBA Most Improved Player Award, recognizing the player judged to have shown the greatest improvement from the previous season.
-
D.
NBAAllSportsmanshipAwardCount
Indicates the number of times an entity has received the NBA Sportsmanship Award.
-
E.
WNBAMostImprovedPlayerAward
Indicates that an entity has received the WNBA Most Improved Player Award, recognizing the player judged to have shown the greatest improvement from a previous season.
- 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_69ca8484838c8190b2049199d22fef70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a3a49608190ad1f65195e4d5cda |
completed | April 1, 2026, 10:20 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a359788190b24f82399489f7fe |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:07 p.m.