Triple
T20079782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blaise Matuidi |
E499965
|
entity |
| Predicate | trophyWonWithClub |
P111762
|
FINISHED |
| Object | Ligue 1 title with Paris Saint-Germain |
—
|
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: Ligue 1 title with Paris Saint-Germain | Statement: [Blaise Matuidi, trophyWonWithClub, Ligue 1 title with Paris Saint-Germain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trophyWonWithClub Context triple: [Blaise Matuidi, trophyWonWithClub, Ligue 1 title with Paris Saint-Germain]
-
A.
cupTitleWonWithClub
Indicates that a specific cup title was won by a player while playing for a particular club.
-
B.
trophyWonWith
Indicates that a particular trophy or award was achieved using, through, or in association with a specified means, tool, team, or context.
-
C.
leagueTitleWonWithClub
chosen
Indicates that a person has won a league title while playing for or being associated with a specific club.
-
D.
trophyWonWithArsenal
Indicates that a trophy was won by a person or team while they were with Arsenal Football Club.
-
E.
majorTitleWonWithClub
Indicates that a person has won a major title or championship while playing for or being associated with a specific club.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6643f93208190ae2a413f88ea9aed |
completed | April 20, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:40 p.m.