Triple
T4122178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arena Football League |
E92638
|
entity |
| Predicate | numberOfPlayersPerSideOnField |
P39852
|
FINISHED |
| Object | 8 |
—
|
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: 8 | Statement: [Arena Football League, numberOfPlayersPerSideOnField, 8]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfPlayersPerSideOnField Context triple: [Arena Football League, numberOfPlayersPerSideOnField, 8]
-
A.
playersPerSideOnField
chosen
Indicates the number of players from each team that are simultaneously present on the field during play.
-
B.
usesNumberOfPlayersOnFieldPerTeam
Indicates that the relationship specifies or depends on how many players each team has on the field at a given time.
-
C.
numberOfPlayersOnIcePerTeam
Indicates the count of players from a single team who are on the ice at the same time during play.
-
D.
sportNumberOfPlayersOnTeam
Indicates the number of players that make up a single team in a given sport.
-
E.
numberOfPlayersLAN
Indicates the number of players that can participate together over a local area network (LAN) in the related 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_69aed9685f70819086932777aec8d959 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69af0246e40081908ad6741a830ca68e |
completed | March 9, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69af01867698819098e4144634b2ec4f |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:41 p.m.