Triple
T4281104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Mary's Stadium |
E97150
|
entity |
| Predicate | capacityRankInPremierLeague |
P55190
|
FINISHED |
| Object | mid-sized |
—
|
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: mid-sized | Statement: [St Mary's Stadium, capacityRankInPremierLeague, mid-sized]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capacityRankInPremierLeague Context triple: [St Mary's Stadium, capacityRankInPremierLeague, mid-sized]
-
A.
premiershipCount
Indicates the number of premiership titles or championships an entity has won.
-
B.
relegatedFromPremierLeague
Indicates that a football club has been demoted from the Premier League to a lower division at the end of a season.
-
C.
LeagueCupTitles
Indicates the number of league cup championships an entity has won.
-
D.
PremierLeagueFoundingMember
Indicates that an entity was one of the original clubs that formed the Premier League at its inception.
-
E.
tierInNationalFootball
Indicates the competitive level or division within a country's national football league system in which an entity (e.g., a club or team) participates.
- F. None of above. chosen
Provenance (4 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_69b34544be3c819084d1ab82d29f90c5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35037b654819087abbb5ea231eefd |
completed | March 12, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69b347fc4c0c8190a7fcd814e27308a5 |
completed | March 12, 2026, 11:10 p.m. |
| PDg | Predicate description generation | batch_69b34e0606488190baadf469a1afc3c2 |
completed | March 12, 2026, 11:36 p.m. |
Created at: March 12, 2026, 11:07 p.m.