Triple
T36783209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2017–18 NBA season |
E908828
|
entity |
| Predicate | rookieStandout |
P52013
|
FINISHED |
| Object | Donovan Mitchell |
—
|
NE NERFINISHED |
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: Donovan Mitchell | Statement: [2017–18 NBA season, rookieStandout, Donovan Mitchell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rookieStandout Context triple: [2017–18 NBA season, rookieStandout, Donovan Mitchell]
-
A.
rookieOPS
Indicates the on-base plus slugging (OPS) performance metric associated with a player during their rookie season.
-
B.
rookieSeason
Indicates the season in which an individual first begins their professional or official participation in a given activity or league.
-
C.
rookiePlayer
Indicates that the player is in their first season or initial stage of professional participation in the sport or league.
-
D.
notableRookie
chosen
Indicates that an individual is recognized as an outstanding or especially noteworthy rookie within a particular field or context.
-
E.
rookieOfTheYearLeague
Indicates that an entity was awarded the Rookie of the Year title in a specified sports league.
- 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_69f76e7a937c81909ed7359641e670f6 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca93bd0481909d6eee9e950001a1 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.