Triple
T33212992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2021–22 NBA G League season |
E850208
|
entity |
| Predicate | featuredTwoWayPlayers |
P203442
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [2021–22 NBA G League season, featuredTwoWayPlayers, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuredTwoWayPlayers Context triple: [2021–22 NBA G League season, featuredTwoWayPlayers, true]
-
A.
featuresPlayers
Indicates that something includes or showcases one or more players as part of its content or composition.
-
B.
featuresPlayersFrom
Indicates that something (such as a work, event, or production) includes or showcases players originating from a specified source, group, or location.
-
C.
featuresReturningPlayers
Indicates that something (such as an event, game, or season) includes or highlights players who are coming back from a previous participation or period.
-
D.
featuresPlayer
Indicates that something includes or prominently presents a particular player as part of its content or composition.
-
E.
featuresTopPlayersFrom
Indicates that something includes or showcases the most prominent or best-performing players from a specified source or group.
- 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_69f3495fb92c819083ce65d0ddee7a76 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a017e7bdfe481909cb4d5bdede6035e |
completed | May 11, 2026, 7 a.m. |
| PD | Predicate disambiguation | batch_6a017defee108190bdf5f98dc415b250 |
completed | May 11, 2026, 6:57 a.m. |
| PDg | Predicate description generation | batch_6a017e7b0ef4819090f82220b73d0888 |
completed | May 11, 2026, 7 a.m. |
Created at: May 1, 2026, 1:30 a.m.