Triple
T27671929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Pilgrims |
E697684
|
entity |
| Predicate | associatedWithStadiumSurface |
P12326
|
FINISHED |
| Object | grass |
—
|
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: grass | Statement: [The Pilgrims, associatedWithStadiumSurface, grass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithStadiumSurface Context triple: [The Pilgrims, associatedWithStadiumSurface, grass]
-
A.
hasSportsSurface
Indicates that one entity (typically a sports facility or area) is characterized by or equipped with a particular type of sports surface.
-
B.
hasCourtSurface
Indicates that something (such as a court or playing area) possesses a specific type of surface.
-
C.
homeFieldSurfaceColor
Indicates the color of the playing surface at an entity’s home field or home venue.
-
D.
homeFieldSurface
chosen
Indicates the type of playing surface used at a team's home field or stadium.
-
E.
associatedWithStadiumLocation
Indicates a relationship where an entity is connected or linked to the location of a specific stadium.
- 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_69ef590d458c81909583290c3cd0478b |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_6a004d0b46148190bcec4ea67acfe170 |
completed | May 10, 2026, 9:16 a.m. |
| PD | Predicate disambiguation | batch_6a004c92283081909f229c1720af155a |
completed | May 10, 2026, 9:14 a.m. |
Created at: April 27, 2026, 2:41 p.m.