Triple
T24467170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Riyad Mahrez |
E617000
|
entity |
| Predicate | roleAtManchesterCity |
P31063
|
FINISHED |
| Object | attacking winger |
—
|
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: attacking winger | Statement: [Riyad Mahrez, roleAtManchesterCity, attacking winger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAtManchesterCity Context triple: [Riyad Mahrez, roleAtManchesterCity, attacking winger]
-
A.
roleInManchesterCity
chosen
Indicates that an entity holds or has held a specific role or position within Manchester City Football Club.
-
B.
roleAtSportsTeam
Indicates the specific position or function an individual holds within a sports team.
-
C.
ChelseaManager
Indicates that a person holds or has held the position of manager (head coach) of Chelsea Football Club.
-
D.
roleInClub
Indicates that an entity holds a specific position or function within a particular club.
-
E.
arsenalRole
Indicates the functional role or position an entity holds within an arsenal or weapons-related 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_69e2d7f197588190889a03e620558059 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f299403a8c819095e31aa2dace6921 |
completed | April 29, 2026, 11:50 p.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:20 a.m.