Triple
T15685139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Williams Ephs |
E380177
|
entity |
| Predicate | rivalrySport |
P60585
|
FINISHED |
| Object | football |
—
|
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: football | Statement: [Williams Ephs, rivalrySport, football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rivalrySport Context triple: [Williams Ephs, rivalrySport, football]
-
A.
sportsRival
Indicates a competitive adversarial relationship between two sports teams, players, or organizations, typically characterized by recurring contests and heightened mutual opposition.
-
B.
rivalryBasis
Indicates the underlying reason, cause, or grounds on which a rivalry between entities is based.
-
C.
rivalryFocus
Indicates a relationship in which one entity is the primary target or center of another entity’s competitive or adversarial rivalry.
-
D.
hasRivalrySport
chosen
Indicates a competitive relationship in which two entities are rivals specifically within the context of a sport or sporting activity.
-
E.
associatedRivalry
Indicates a relationship where one entity is linked to another as its rival, competitor, or opposing counterpart.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f4b73d881908ec0f21393a01969 |
completed | April 16, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69deda8c856c8190882330114f9a1a5f |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:44 a.m.