Triple
T12946131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Broyles |
E309770
|
entity |
| Predicate | teamNationalChampionship |
P18665
|
FINISHED |
| Object | 1964 college football national championship (Arkansas Razorbacks) |
—
|
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: 1964 college football national championship (Arkansas Razorbacks) | Statement: [Frank Broyles, teamNationalChampionship, 1964 college football national championship (Arkansas Razorbacks)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamNationalChampionship Context triple: [Frank Broyles, teamNationalChampionship, 1964 college football national championship (Arkansas Razorbacks)]
-
A.
collegeTeamChampionships
Indicates the championships or titles that a college sports team has won.
-
B.
numberOfNationalChampionships
Indicates the total count of national championship titles an entity has won.
-
C.
nationalChampionshipTitle
chosen
Indicates that an entity has won a national-level championship title in a particular sport, competition, or field.
-
D.
collegeChampionshipTeam
Indicates that a team is the winner of a specified college-level championship competition.
-
E.
NCAAChampionshipCount
Indicates the number of NCAA championships an entity has won.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e59a4c88190907d05b8d57dae89 |
completed | April 10, 2026, 10:48 p.m. |
| PD | Predicate disambiguation | batch_69d97db69f548190a1a693bc0d6c191a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 5:43 p.m.