Triple
T16041725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | af2 |
E389111
|
entity |
| Predicate | championshipGameName |
P51268
|
FINISHED |
| Object |
ArenaCup
ArenaCup is the championship game and title of the now-defunct arenafootball2 (af2) indoor American football league.
|
E1190776
|
NE FINISHED |
How this triple was built (4 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: ArenaCup | Statement: [af2, championshipGameName, ArenaCup]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ArenaCup Context triple: [af2, championshipGameName, ArenaCup]
-
A.
ArenaBowl
ArenaBowl is the annual championship game of the Arena Football League that determines the league's champion.
-
B.
Super Bowl
The Super Bowl is the annual championship game of the National Football League and one of the most-watched sporting and entertainment events in the United States.
-
C.
NFL Championship
The NFL Championship was the pre-Super Bowl title game that determined the league’s champion each season from 1933 through 1965.
-
D.
Hall of Fame Game
The Hall of Fame Game is an annual NFL preseason matchup in Canton, Ohio that traditionally kicks off the league’s exhibition schedule as part of Pro Football Hall of Fame induction festivities.
-
E.
World Bowl
The World Bowl was the championship game of NFL Europe, determining the league’s annual title winner.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: ArenaCup Triple: [af2, championshipGameName, ArenaCup]
Generated description
ArenaCup is the championship game and title of the now-defunct arenafootball2 (af2) indoor American football league.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ArenaCup Target entity description: ArenaCup is the championship game and title of the now-defunct arenafootball2 (af2) indoor American football league.
-
A.
ArenaBowl
ArenaBowl is the annual championship game of the Arena Football League that determines the league's champion.
-
B.
Super Bowl
The Super Bowl is the annual championship game of the National Football League and one of the most-watched sporting and entertainment events in the United States.
-
C.
NFL Championship
The NFL Championship was the pre-Super Bowl title game that determined the league’s champion each season from 1933 through 1965.
-
D.
Hall of Fame Game
The Hall of Fame Game is an annual NFL preseason matchup in Canton, Ohio that traditionally kicks off the league’s exhibition schedule as part of Pro Football Hall of Fame induction festivities.
-
E.
World Bowl
The World Bowl was the championship game of NFL Europe, determining the league’s annual title winner.
- F. None of above. chosen
Provenance (5 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e18340686881909135fc43a0a71b20 |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbd77c5481908644742a8a8f3e68 |
completed | May 10, 2026, 1:13 a.m. |
| NEDg | Description generation | batch_69ffdc4f3d488190a5d1bffd4432ac32 |
completed | May 10, 2026, 1:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffdd0392e08190af42a0cdc5dd4c1f |
completed | May 10, 2026, 1:18 a.m. |
Created at: April 10, 2026, 4:56 a.m.