Triple
T37067844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winterslag |
E917495
|
entity |
| Predicate | hasSuccessorSportEntity |
P75330
|
FINISHED |
| Object | KRC Genk |
—
|
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: KRC Genk | Statement: [Winterslag, hasSuccessorSportEntity, KRC Genk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSuccessorSportEntity Context triple: [Winterslag, hasSuccessorSportEntity, KRC Genk]
-
A.
hasSuccessorTeam
chosen
Indicates that one team is the direct successor or continuation of another team, typically following rebranding, relocation, or organizational change.
-
B.
successorSport
Indicates that one sport has replaced or followed another as its successor in some official or historical context.
-
C.
hasSuccessorClubName
Indicates that one club’s name is followed or replaced by another club’s name, typically due to succession or rebranding.
-
D.
hasSuccessorShip
Indicates that one entity is the ship that follows or replaces another ship in a sequence or lineage.
-
E.
hasSuccessorFacilityType
Indicates that one facility type is followed or replaced by another facility type in a sequence or evolution over time.
- 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_69f76e95fa40819091e14681087ae5e4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00332eaa0c8190a69ea895576bb0ee |
completed | May 10, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_6a0032b2ea80819083b89ebb88165933 |
completed | May 10, 2026, 7:24 a.m. |
Created at: May 3, 2026, 4:14 p.m.