Triple
T4555564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Round of NCAA Division I Men's Basketball Tournament |
E120468
|
entity |
| Predicate | matchupPattern |
P10212
|
FINISHED |
| Object | 1 vs 16 seed |
—
|
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: 1 vs 16 seed | Statement: [First Round of NCAA Division I Men's Basketball Tournament, matchupPattern, 1 vs 16 seed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchupPattern Context triple: [First Round of NCAA Division I Men's Basketball Tournament, matchupPattern, 1 vs 16 seed]
-
A.
matchOf
Indicates that one entity is a specific match, counterpart, or corresponding instance of another entity within a defined context or set.
-
B.
matchType
chosen
Indicates the specific category or nature of how two or more entities correspond or align with each other within a given context.
-
C.
matchupFrequency
Indicates how often a particular pair or set of entities are matched or paired against each other within a given context or timeframe.
-
D.
matchResult
Indicates the outcome or final status produced by a particular match or game between participants.
-
E.
matchTypes
Indicates that two or more entities share the same type or category according to a specified classification.
- 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_69bd4636f1648190a701445c2fcd9c17 |
completed | March 20, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69bd5813af948190b10b02dadf6496bf |
completed | March 20, 2026, 2:22 p.m. |
| PD | Predicate disambiguation | batch_69bd5223423c81908317351b58cff5f5 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:09 p.m.