Triple
T24263103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jake Taylor |
E604760
|
entity |
| Predicate | keyGame |
P155370
|
FINISHED |
| Object | one-game playoff against the New York Yankees |
—
|
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: one-game playoff against the New York Yankees | Statement: [Jake Taylor, keyGame, one-game playoff against the New York Yankees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyGame Context triple: [Jake Taylor, keyGame, one-game playoff against the New York Yankees]
-
A.
videoGame
Indicates that one entity is a video game associated with, created by, or otherwise related to another entity.
-
B.
keyOftenPlayedIn
Indicates that a particular musical key is frequently used or performed in association with a given piece, artist, or context.
-
C.
featuresGame
Indicates that something (such as a platform, service, or collection) includes or presents a particular game as part of its offerings.
-
D.
games
Indicates that one entity participates in, is associated with, or is characterized by playing or engaging in games with another entity.
-
E.
primaryGame
Indicates that one game is the main or most significant game associated with an entity (such as a person, team, or event) among possibly several games.
- 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_69e29544c29c8190b023606eafe5d36a |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28c691eb08190b6fbda8f187d7427 |
completed | April 29, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69f1c450aa508190bc9d372a5f6ee47a |
completed | April 29, 2026, 8:41 a.m. |
| PDg | Predicate description generation | batch_69f1c6d4e99081909f61899eccafb73e |
completed | April 29, 2026, 8:52 a.m. |
Created at: April 18, 2026, 12:06 a.m.