Triple
T9995854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Reigns |
E197198
|
entity |
| Predicate | royalRumbleWinner |
P91481
|
FINISHED |
| Object | 2015 |
—
|
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: 2015 | Statement: [Roman Reigns, royalRumbleWinner, 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: royalRumbleWinner Context triple: [Roman Reigns, royalRumbleWinner, 2015]
-
A.
conferenceOfChampion
Indicates a relationship where a conference or event is held to recognize, feature, or determine a champion.
-
B.
WWEWorldHeavyweightChampionLeavingEvent
Indicates that an individual who holds the WWE World Heavyweight Championship title is departing from an event venue.
-
C.
subsequentChampion
Indicates that one entity became the champion in a competition or context after another entity had previously held the champion title.
-
D.
associatedWomanOfVictory
Indicates a relationship in which a woman is connected or linked to a particular victory, such as by contributing to, representing, or being honored in relation to that victory.
-
E.
defendingChampion
Indicates that an entity currently holds a title or championship and is defending it against challengers.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcb9af6a88190942cc4991bd373c1 |
completed | April 2, 2026, 1:51 a.m. |
| PD | Predicate disambiguation | batch_69cd1da07db88190945bcdab3ca82e71 |
completed | April 1, 2026, 1:29 p.m. |
| PDg | Predicate description generation | batch_69cd358386f48190833c862b5b8c04b2 |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:50 p.m.