Triple
T5349001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theme from New York, New York |
E124125
|
entity |
| Predicate | frequentlyPlayedAt |
P60269
|
FINISHED |
| Object | New York Yankees home 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: New York Yankees home games | Statement: [Theme from New York, New York, frequentlyPlayedAt, New York Yankees home games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frequentlyPlayedAt Context triple: [Theme from New York, New York, frequentlyPlayedAt, New York Yankees home games]
-
A.
frequentlyPerformedAt
chosen
Indicates that an action or event occurs regularly or with high frequency at a particular location or context.
-
B.
playedAfter
Indicates that one event, performance, or action occurred later in time than another.
-
C.
frequentlyVisitedBy
Indicates that an entity is regularly or often visited by another entity.
-
D.
playedFrom
Indicates that an action of playing (such as media playback or a performance) originated from a particular source or starting point.
-
E.
frequentPerformance
Indicates that an entity regularly or repeatedly carries out a particular performance or activity over a period of time.
- 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_69bd464be27081908807b40b75c1bbae |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd860ea7088190ad7be14132927d17 |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.