Triple
T33941524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memorial Day Miracle |
E870178
|
entity |
| Predicate | wasAgainstTeam |
P48918
|
FINISHED |
| Object | Portland Trail Blazers |
—
|
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: Portland Trail Blazers | Statement: [Memorial Day Miracle, wasAgainstTeam, Portland Trail Blazers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasAgainstTeam Context triple: [Memorial Day Miracle, wasAgainstTeam, Portland Trail Blazers]
-
A.
wasOpponentOf
Indicates that one entity competed or conflicted against another as an adversary in some contest, game, or confrontation.
-
B.
teamOpposed
Indicates that one team is in opposition or conflict with another team, such as being rivals or competing against each other.
-
C.
opposingTeamInNotableEvent
chosen
Indicates that one entity served as the opposing team of another entity in a specific notable event or competition.
-
D.
hasOpposingTeamsLedBy
Indicates a relationship where a competitive event or context features two opposing teams, each directed or managed by a specific leader.
-
E.
hasOpposingAlliance
Indicates that two entities belong to alliances or factions that are in direct opposition or conflict with each other.
- 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.