Triple
T29521433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Michigan Broncos football |
E748945
|
entity |
| Predicate | 2016Achievement |
P9672
|
FINISHED |
| Object | undefeated regular season |
—
|
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: undefeated regular season | Statement: [Western Michigan Broncos football, 2016Achievement, undefeated regular season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 2016Achievement Context triple: [Western Michigan Broncos football, 2016Achievement, undefeated regular season]
-
A.
achievementDefinition
Indicates that one entity specifies or defines the criteria, properties, or structure of an achievement associated with another entity.
-
B.
associatedAchievement
chosen
Indicates a relationship where one entity is linked to, or recognized in connection with, a particular achievement.
-
C.
coAchieved
Indicates that two or more entities jointly accomplished or attained the same goal, outcome, or achievement.
-
D.
achievementScope
Indicates the extent or domain within which an achievement is recognized, measured, or considered valid.
-
E.
placeOfAchievement
Indicates the location where an entity accomplished or attained a particular achievement or notable success.
- 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_69f0bd46d99c81908ba9d01cc1dbef7d |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c9973b08190bbb12bd759f0578e |
completed | May 2, 2026, 9:28 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:41 p.m.