Triple
T35636363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Owens and Sami Zayn defeated The Usos |
E1029730
|
entity |
| Predicate | formerChampionTeam |
P202269
|
FINISHED |
| Object | The Usos |
—
|
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: The Usos | Statement: [Kevin Owens and Sami Zayn defeated The Usos, formerChampionTeam, The Usos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerChampionTeam Context triple: [Kevin Owens and Sami Zayn defeated The Usos, formerChampionTeam, The Usos]
-
A.
formerTeam2Name
Indicates that an entity was previously associated with a second former team identified by this name.
-
B.
hadChampionTeam
Indicates that an entity (such as a league, season, or competition) had a specific team recognized as its champion.
-
C.
formerLeagueTeam
Indicates that an entity was previously a member team of a particular sports league but is no longer part of that league.
-
D.
team1LaterKnownAs
Indicates that the first team was later renamed to or became known by the identity of the second team.
-
E.
formerTeamNameInRivalry
Indicates that a team previously had a specific name during the period of a particular rivalry.
- 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_69f76e087bdc8190a4794bf9c0bd7634 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a00694f72888190983fee7d687a6daa |
completed | May 10, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_6a00685dbf44819098ea0c86bb9e50d8 |
completed | May 10, 2026, 11:13 a.m. |
| PDg | Predicate description generation | batch_6a00694e9e008190b7c941d2f7527dff |
completed | May 10, 2026, 11:17 a.m. |
Created at: May 3, 2026, 4:05 p.m.