Triple
T24323664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2020–2021 Premier League |
E613037
|
entity |
| Predicate | topAssistsPlayer |
P57620
|
FINISHED |
| Object | Harry Kane |
—
|
NE NERFINISHED |
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: Harry Kane | Statement: [2020–2021 Premier League, topAssistsPlayer, Harry Kane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topAssistsPlayer Context triple: [2020–2021 Premier League, topAssistsPlayer, Harry Kane]
-
A.
topAssistsLeader
chosen
Indicates that the subject is the leading provider of assists, typically having the highest number of assists in a given group, league, or time period.
-
B.
topAssistsAssistsPerGame
Indicates that the subject ranks among the top performers in terms of average assists made per game.
-
C.
mostAssistsPlayer
Indicates that the subject is the player who recorded the highest number of assists for the referenced game, season, team, or context.
-
D.
mostAssistsNumber
Indicates that an entity holds the highest number of assists recorded within a given context or comparison set.
-
E.
assistsLeaderTeam
Indicates that an entity provides help or support to the leader’s team in carrying out its activities or responsibilities.
- 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_69e2d7db6d5c819091194918157a7c1f |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292ae127881909ef1772278181ce3 |
completed | April 29, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69f287ad30048190b3ad3613486f277f |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:53 a.m.