Triple
T30719238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WWE Backlash 2023 |
E782105
|
entity |
| Predicate | wrestlerInvolved |
P170068
|
FINISHED |
| Object | Roman Reigns |
—
|
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: Roman Reigns | Statement: [WWE Backlash 2023, wrestlerInvolved, Roman Reigns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wrestlerInvolved Context triple: [WWE Backlash 2023, wrestlerInvolved, Roman Reigns]
-
A.
wrestledWith
Indicates that one entity engaged in a physical wrestling contest or struggle with another entity.
-
B.
wrestledFor
Indicates that one entity engaged in a wrestling match or competition on behalf of, or as a representative of, another entity (such as a team, organization, or country).
-
C.
managedWrestler
Indicates that one entity served as the manager of another entity in a professional wrestling context.
-
D.
pinnedWrestler
Indicates that one wrestler has held another wrestler's shoulders to the mat in a position that could result in a pin or fall.
-
E.
wrestlingPromotionAppearedIn
Indicates that a wrestler or wrestling-related entity made an appearance in a specific wrestling promotion or organization.
- 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_69f224acd24481908ed5f96f0d69b5dd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68c583438819093b812f11327eb60 |
completed | May 2, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69f688034580819086a0f9100645f8ba |
completed | May 2, 2026, 11:25 p.m. |
Created at: April 29, 2026, 8:36 p.m.