Triple
T11876324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blunder Bowl |
E282535
|
entity |
| Predicate | appliedToEventType |
P14526
|
FINISHED |
| Object | American football championship game |
—
|
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: American football championship game | Statement: [Blunder Bowl, appliedToEventType, American football championship game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliedToEventType Context triple: [Blunder Bowl, appliedToEventType, American football championship game]
-
A.
appliedInEvent
Indicates that an action, method, or concept is utilized or carried out within the context of a specific event.
-
B.
appearsAtEventType
Indicates that an entity is present or participates in an event of a specified type.
-
C.
hasEventType
chosen
Indicates that an event is associated with, or classified under, a specific type or category of event.
-
D.
appliedToEntityType
Indicates that something (such as a rule, constraint, or operation) is specifically applied to entities of a given type.
-
E.
appliedWhen
Indicates the condition, time, or circumstances under which something (such as a rule, action, or effect) becomes applicable or is carried out.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d39d2934819093b9f7006f45e5cb |
completed | April 10, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69d8bb272f88819090c37c944c5a60ab |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:44 p.m.