Triple
T405498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFC East |
E9373
|
entity |
| Predicate | usesTiebreakers |
P6631
|
FINISHED |
| Object | NFL tiebreaking procedures |
—
|
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: NFL tiebreaking procedures | Statement: [AFC East, usesTiebreakers, NFL tiebreaking procedures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTiebreakers Context triple: [AFC East, usesTiebreakers, NFL tiebreaking procedures]
-
A.
tiebreaker
chosen
Indicates that one entity serves as the deciding factor used to break a tie between two or more otherwise equal options or outcomes.
-
B.
usesPitchClock
Indicates that an entity employs or is governed by a pitch clock to regulate the timing of pitches.
-
C.
hasDesignatedPlayerRule
Indicates that a sports league or competition uses a designated player rule allowing certain players to be treated differently for roster or salary purposes.
-
D.
playedUnderRulesOf
Indicates that an activity or game was conducted in accordance with a specified set of rules or regulations.
-
E.
hasHistoricalTieTo
Indicates a relationship where one entity is historically connected or linked to another through past events, associations, or influences.
- 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_69a2e8004cb88190b92ed1add6abf41a |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2eca37fe881909802126952dfdd59 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e97066e8819083cc1b3a421b9650 |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.