Triple
T6563336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1980s NBA |
E153839
|
entity |
| Predicate | definingMatchup |
P71824
|
FINISHED |
| Object | Magic Johnson vs Larry Bird |
—
|
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: Magic Johnson vs Larry Bird | Statement: [1980s NBA, definingMatchup, Magic Johnson vs Larry Bird]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: definingMatchup Context triple: [1980s NBA, definingMatchup, Magic Johnson vs Larry Bird]
-
A.
matchOf
Indicates that one entity is a specific match, counterpart, or corresponding instance of another entity within a defined context or set.
-
B.
matchupFrequency
Indicates how often a particular pair or set of entities are matched or paired against each other within a given context or timeframe.
-
C.
decidingMatchFor
Indicates a relationship where one entity is chosen or determined as the appropriate or final match for another entity among possible alternatives.
-
D.
finalsMatchup
Indicates that two competitors or teams are paired to face each other in the final round of a competition or tournament.
-
E.
featuredMatchType
Indicates the specific category or kind of match that is highlighted or given special prominence.
- 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_69c6880cb35881909b763eb0125236b9 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6c1b15d3481908ae66e3d7564b352 |
completed | March 27, 2026, 5:43 p.m. |
| PD | Predicate disambiguation | batch_69c6acf6d4148190914b19e9affd8c76 |
completed | March 27, 2026, 4:14 p.m. |
| PDg | Predicate description generation | batch_69c6c1b007148190b5164d6d09584cdf |
completed | March 27, 2026, 5:43 p.m. |
Created at: March 27, 2026, 1:52 p.m.