Triple
T24913473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | College Football Playoff Selection Committee |
E623909
|
entity |
| Predicate | selectsNumberOfTeams |
P6986
|
FINISHED |
| Object | 4 |
—
|
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: 4 | Statement: [College Football Playoff Selection Committee, selectsNumberOfTeams, 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: selectsNumberOfTeams Context triple: [College Football Playoff Selection Committee, selectsNumberOfTeams, 4]
-
A.
hasNumberOfTeams
chosen
Indicates the quantity of teams associated with or contained by a given entity.
-
B.
qualifiedTeamsCount
Indicates the number of teams that have successfully met the criteria to qualify for a given stage, event, or competition.
-
C.
numberOfTeamsLater
Indicates that one entity has a greater number of teams than another entity at a later point in time.
-
D.
numberOfTeamsVariesBetween
Indicates that the count of teams involved changes within a specified range or across different instances or conditions.
-
E.
numberOfPlayersPerTeam
Indicates the quantity of players that are assigned to or allowed on each team in a given context.
- 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_69e2fac889c081908e9ff686cb428e5a |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cf017a88190b4985b11159c907d |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 5:28 a.m.