Triple
T749399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polo Grounds |
E15412
|
entity |
| Predicate | hostedWorldSeries |
P527
|
FINISHED |
| Object | multiple World Series games |
—
|
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: multiple World Series games | Statement: [Polo Grounds, hostedWorldSeries, multiple World Series games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostedWorldSeries Context triple: [Polo Grounds, hostedWorldSeries, multiple World Series games]
-
A.
sportsEventHosted
chosen
Indicates that a particular sports event was organized, arranged, or held by a specified host entity (such as a venue, organization, or city).
-
B.
currentWorldSeriesHomeFieldRule
Indicates the rule currently in effect that determines which league or team receives home-field advantage in the World Series.
-
C.
hostStadium
Indicates that a particular stadium serves as the venue where an event, team, or competition is hosted.
-
D.
nextWorldSeries
Indicates that one entity is the World Series event that immediately follows another in chronological order.
-
E.
resultingWorldSeries
Indicates the specific World Series event or outcome that results from a given preceding condition, season, or set of circumstances.
- 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_69a493599a0081908da65f3407af1ef2 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a6304e0c8190827fb57c5cac2da9 |
completed | March 1, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69a4a5004f708190a984ee221716e19c |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.