Triple
T24707731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018–2019 Premier League |
E611942
|
entity |
| Predicate | fewestGoalsConceded |
P128971
|
FINISHED |
| Object | 22 |
—
|
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: 22 | Statement: [2018–2019 Premier League, fewestGoalsConceded, 22]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fewestGoalsConceded Context triple: [2018–2019 Premier League, fewestGoalsConceded, 22]
-
A.
fewestGoalsConcededRecordScope
Indicates the specific context or scope (such as competition, season, or time period) within which a record for the fewest goals conceded is defined.
-
B.
fewestGoalsTeam
Indicates the team that has conceded or scored the lowest number of goals compared to all other teams in the relevant context.
-
C.
goalsConceded
chosen
Indicates the number of goals a team or player has allowed the opposing side to score.
-
D.
fewestLossesTeam
Indicates that the referenced team is the one with the smallest number of losses compared to all other teams in the relevant set or competition.
-
E.
mostCleanSheetsNumber
Indicates the number of times an entity holds the record for having the most clean sheets (games without conceding a goal) in a given context or competition.
- 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_69e2c4d9c24c8190a3712d74327f0c6e |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f422aee0408190899efe7e24ef2b40 |
completed | May 1, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69f420e92cc88190a803aecdae78a051 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 3:24 a.m.