Triple
T25969615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2019 NCAA Division I men's basketball tournament |
E645768
|
entity |
| Predicate | playInRoundCity |
P107191
|
FINISHED |
| Object | Dayton, Ohio |
—
|
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: Dayton, Ohio | Statement: [2019 NCAA Division I men's basketball tournament, playInRoundCity, Dayton, Ohio]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playInRoundCity Context triple: [2019 NCAA Division I men's basketball tournament, playInRoundCity, Dayton, Ohio]
-
A.
playInGameCity
chosen
Indicates that an entity participates in or plays in a game that takes place in a specified city.
-
B.
openingGameCity
Indicates the city where an opening game or initial match of an event takes place.
-
C.
game3City
Indicates that a game or match (in a series or sequence) takes place in, or is associated with, a particular city.
-
D.
game6City
Indicates that a game or sporting event took place in, or is associated with, a particular city.
-
E.
game5City
Indicates that a particular game or sporting event took place in, or is associated with, a specific city.
- 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_69e77e8768648190b27bb578f14bcb88 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f604cd91088190a2c9ab800dcaec37 |
completed | May 2, 2026, 2:06 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:50 a.m.