Triple
T3306359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pat Tilley |
E69458
|
entity |
| Predicate | rulesOfSport |
P6601
|
FINISHED |
| Object | NFL rules of American football |
—
|
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 rules of American football | Statement: [Pat Tilley, rulesOfSport, NFL rules of American football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rulesOfSport Context triple: [Pat Tilley, rulesOfSport, NFL rules of American football]
-
A.
esportDiscipline
Indicates that one entity is a specific esports game or discipline in which the other entity participates or is involved.
-
B.
playedUnderRulesOf
chosen
Indicates that an activity or game was conducted in accordance with a specified set of rules or regulations.
-
C.
sportRestriction
Indicates a limitation, prohibition, or specific condition placed on participating in a sport or sports-related activity.
-
D.
traditionalSport
Indicates that an entity is a sport practiced within a culture or community that has been passed down over generations and is recognized as part of traditional or heritage activities.
-
E.
hasRulebook
Indicates that one entity possesses, is governed by, or is associated with a specific rulebook.
- 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0caa0988190872fc7648e64571f |
completed | March 8, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69ada42625308190be257f16a623a410 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:11 p.m.