Triple
T14317843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Giants |
E355002
|
entity |
| Predicate | playsContactSport |
P55627
|
FINISHED |
| Object | 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: American football | Statement: [New York Giants, playsContactSport, American football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playsContactSport Context triple: [New York Giants, playsContactSport, American football]
-
A.
isContactSport
Indicates that the activity involves significant physical contact between participants as an inherent and expected part of play.
-
B.
primarySport
Indicates the main sport with which an entity (such as a person, team, or organization) is most closely associated or primarily involved.
-
C.
sportsInvolvement
Indicates the nature or extent of an entity’s participation in, association with, or role within a sport or sporting activity.
-
D.
primarySports
chosen
Indicates that a particular sport is the main or most important sport associated with an entity (such as a person, team, or organization).
-
E.
playsAssociationFootballIn
Indicates that an entity participates in playing association football (soccer) within or for a specified place, organization, or 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de883a93548190ac671b001d15d0bd |
completed | April 14, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69de2a9515f4819081aabf251bca5878 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:13 a.m.