Triple
T6176933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | East Midlands derby |
E137842
|
entity |
| Predicate | hasTrophySince |
P28247
|
FINISHED |
| Object | Brian Clough Trophy introduced in 2007 |
—
|
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: Brian Clough Trophy introduced in 2007 | Statement: [East Midlands derby, hasTrophySince, Brian Clough Trophy introduced in 2007]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTrophySince Context triple: [East Midlands derby, hasTrophySince, Brian Clough Trophy introduced in 2007]
-
A.
hasTrophyStatus
Indicates that an entity possesses a particular trophy-related status or classification.
-
B.
hasRelatedTrophy
chosen
Indicates that there exists a trophy that is associated with, linked to, or relevant to the given entity.
-
C.
hasTrophyForm
Indicates that one entity exists in, or is characterized by, a special trophy-like form or version of another entity.
-
D.
hasPredecessorTrophy
Indicates that one trophy directly precedes another trophy in a defined sequence or order.
-
E.
hasMedalCount
Indicates the relationship between an entity and the number of medals it possesses or has been awarded.
- 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_69c008a80f748190ba3d07ffc81acb29 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05dc87bc48190834042d9c41d5b86 |
completed | March 22, 2026, 9:23 p.m. |
| PD | Predicate disambiguation | batch_69c055f7f12881908e21c04e9b752ba4 |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:18 p.m.