Triple
T13503363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1957 NFL Championship Game |
E320946
|
entity |
| Predicate | homeTeamChampionshipsWonWithThisGame |
P13593
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [1957 NFL Championship Game, homeTeamChampionshipsWonWithThisGame, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeTeamChampionshipsWonWithThisGame Context triple: [1957 NFL Championship Game, homeTeamChampionshipsWonWithThisGame, 3]
-
A.
homeTeamChampion
Indicates that the team playing at home is the champion or title-holding team in the given context.
-
B.
gamesWonBy
Indicates the number of games that have been won by a particular entity in a given context.
-
C.
winsWithTeam
Indicates that an entity achieves a victory as a member of, or in conjunction with, a specific team.
-
D.
game4WinningTeam
Indicates which team won the specified game.
-
E.
homeTeamTitleCountAfterMatch
chosen
Indicates the total number of titles the home team has accumulated after the completion of the referenced match.
- 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_69d807629d6c8190998f1b9bb12d2ed0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaf810e248190a060481004503f96 |
completed | April 12, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69dbae0b63748190b5e207f84b2532ea |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:43 p.m.