Triple
T34942896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luz |
E1007773
|
entity |
| Predicate | showedSportsmanshipTo |
P139572
|
FINISHED |
| Object | Jesse Owens |
—
|
NE NERFINISHED |
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: Jesse Owens | Statement: [Luz, showedSportsmanshipTo, Jesse Owens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: showedSportsmanshipTo Context triple: [Luz, showedSportsmanshipTo, Jesse Owens]
-
A.
sportsAchievement
Indicates a relationship where an entity attains or is recognized for a notable accomplishment in a sports context.
-
B.
describesGallantryOf
Indicates a relationship where one entity characterizes, explains, or details the gallant or brave behavior of another entity.
-
C.
competitionWonWith
Indicates that a competition was won using, involving, or in association with a particular participant, method, tool, or resource.
-
D.
fairPlayAspect
chosen
Indicates that the relationship or action pertains to an aspect or dimension of fair play, such as fairness, sportsmanship, or equitable conduct within a rule-governed context.
-
E.
sportsSkill
Indicates that an entity possesses a particular ability, proficiency, or level of competence in performing a sport or sports-related activity.
- 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_69f76dc513fc819084a1ff52abbfa5bc |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782c98fa08190870b68de2c1ff26a |
completed | May 3, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_69f781020cc4819088c40cb8589504e4 |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.