Triple
T18183072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epsom Derby Festival |
E435338
|
entity |
| Predicate | ageQualificationMainRace |
P48792
|
FINISHED |
| Object | three-year-old thoroughbreds |
—
|
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: three-year-old thoroughbreds | Statement: [Epsom Derby Festival, ageQualificationMainRace, three-year-old thoroughbreds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageQualificationMainRace Context triple: [Epsom Derby Festival, ageQualificationMainRace, three-year-old thoroughbreds]
-
A.
raceTypeByAge
chosen
Indicates that the type or category of a race is determined or classified based on the ages of its participants.
-
B.
olympicEligibilityRule
Indicates that a specific rule or condition determines whether an athlete or team is eligible to participate in the Olympic Games.
-
C.
ageStatus
Indicates the relationship between an entity and its classification into an age-related category or status (e.g., minor, adult, senior).
-
D.
qualifyingFor
Indicates that one entity meets the necessary conditions or criteria to be eligible for another entity, status, or action.
-
E.
hasRoleInRace
Indicates that an entity participates in a race with a specific role or function.
- 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dffc432c8190af53da5256dc476c |
completed | April 19, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69e4331e92408190ad607ba4956a3897 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:31 a.m.