Triple
T27860103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derek Pavis Stand |
E704201
|
entity |
| Predicate | sportFacilityType |
P25287
|
FINISHED |
| Object | football ground stand |
—
|
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: football ground stand | Statement: [Derek Pavis Stand, sportFacilityType, football ground stand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportFacilityType Context triple: [Derek Pavis Stand, sportFacilityType, football ground stand]
-
A.
sportsFacility
Indicates that one entity is a sports facility where sports or physical activities can take place for the other entity.
-
B.
OlympicVenueType
Indicates the specific type or classification of a venue used for Olympic events.
-
C.
sportsVenueFor
Indicates that a venue is used as the location or facility where a particular sport or sporting event takes place.
-
D.
sportsInfrastructureDevelopedFor
Indicates that sports-related facilities or structures have been created, improved, or established for the benefit or use of a particular entity.
-
E.
hasSportsVenueType
chosen
Indicates that a sports venue is classified as being of a specific type or category (e.g., stadium, arena, court).
- 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_69ef840e614c8190a88cf9638c14a265 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6617ba4a88190bfc5c305acb4f93f |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 27, 2026, 6:17 p.m.